Bawwab: Top 302 scan

academic-paper-reviewer

Not malicious, needs a look Reviewed: false alarm

Bawwab's static rules found patterns that deserve a human look. This is not a finding that the package is malicious; the review notes below say what each pattern turned out to be.

Why it was flagged

The static rules marked this “Not malicious, needs a look” because of:

Kind
Skill
Source
github
Repository
Imbad0202/academic-research-skills / academic-paper-reviewer
Commit
bd57330f63f4b089dde8fdef9bf5f009ecc89f0c
Popularity
57,880 GitHub stars (2026-11-20)
Link
https://github.com/Imbad0202/academic-research-skills/tree/bd57330f63f4b089dde8fdef9bf5f009ecc89f0c/academic-paper-reviewer
Scanned
2026-11-20T22:41:37+00:00
Scan time
0.3 s
Scanned as
skill
Review note: All hits are defensive anti-injection wording and maintainer comments; nothing hidden.

Findings (11)

injection.override: Tries to override the AI's instructions high

agents/devils_advocate_reviewer_agent.md:109

OWASP LLM LLM01 Prompt InjectionOWASP LLM LLM07 System Prompt LeakageOWASP Agentic ASI01 Agent Goal HijackMITRE ATLAS AML.T0051.001 LLM Prompt Injection: IndirectMITRE ATLAS AML.T0110.000 AI Agent Tool Poisoning: Definition and InstructionsMITRE ATLAS AML.T0069.002 Discover LLM System Information: System PromptCWE CWE-1427 Improper Neutralization of Input Used for LLM Prompting

ignore prior instructions

What this means: Text read by the AI that says to ignore earlier instructions, reveal the system prompt or hide things from you is a classic prompt-injection attempt.

The rule's general advice: Do not install; the text is trying to steer the assistant against you. (see the review note for this case)

Known false alarm

The phrase appears inside an instruction telling the reviewer agent to treat the manuscript and its own earlier output as data, and to ignore embedded lines such as "ignore previous instructions". It is a defence against prompt injection.

Reviewed by Claude (AI-assisted review), 2026-11-21

injection.html-comment: Hidden instruction in an HTML comment med

agents/devils_advocate_reviewer_agent.md:39

OWASP LLM LLM01 Prompt InjectionOWASP Agentic ASI01 Agent Goal HijackMITRE ATLAS AML.T0051.001 LLM Prompt Injection: IndirectMITRE ATLAS AML.T0068 LLM Prompt ObfuscationCWE CWE-1427 Improper Neutralization of Input Used for LLM Prompting

<!-- Canonical inline-prompt source: ../references/reviewer_sprint_prompt_source.md. The dispatched H3 bodies stay inline and are byte-sync-linted; this pointer is not a runtime include. -->

What this means: HTML comments are invisible when a document is rendered but are still read by the AI, so they can carry instructions meant to stay unseen.

The rule's general advice: Read the comment; remove it or do not install. (see the review note for this case)

Known false alarm

Maintainer comment pointing to the canonical prompt source file and noting the text is lint-checked for sync. It gives the AI no instructions.

Reviewed by Claude (AI-assisted review), 2026-11-21

injection.override: Tries to override the AI's instructions high

agents/domain_reviewer_agent.md:108

OWASP LLM LLM01 Prompt InjectionOWASP LLM LLM07 System Prompt LeakageOWASP Agentic ASI01 Agent Goal HijackMITRE ATLAS AML.T0051.001 LLM Prompt Injection: IndirectMITRE ATLAS AML.T0110.000 AI Agent Tool Poisoning: Definition and InstructionsMITRE ATLAS AML.T0069.002 Discover LLM System Information: System PromptCWE CWE-1427 Improper Neutralization of Input Used for LLM Prompting

ignore prior instructions

What this means: Text read by the AI that says to ignore earlier instructions, reveal the system prompt or hide things from you is a classic prompt-injection attempt.

The rule's general advice: Do not install; the text is trying to steer the assistant against you. (see the review note for this case)

Known false alarm

The phrase appears inside an instruction telling the reviewer agent to treat the manuscript and its own earlier output as data, and to ignore embedded lines such as "ignore previous instructions". It is a defence against prompt injection.

Reviewed by Claude (AI-assisted review), 2026-11-21

injection.html-comment: Hidden instruction in an HTML comment med

agents/domain_reviewer_agent.md:38

OWASP LLM LLM01 Prompt InjectionOWASP Agentic ASI01 Agent Goal HijackMITRE ATLAS AML.T0051.001 LLM Prompt Injection: IndirectMITRE ATLAS AML.T0068 LLM Prompt ObfuscationCWE CWE-1427 Improper Neutralization of Input Used for LLM Prompting

<!-- Canonical inline-prompt source: ../references/reviewer_sprint_prompt_source.md. The dispatched H3 bodies stay inline and are byte-sync-linted; this pointer is not a runtime include. -->

What this means: HTML comments are invisible when a document is rendered but are still read by the AI, so they can carry instructions meant to stay unseen.

The rule's general advice: Read the comment; remove it or do not install. (see the review note for this case)

Known false alarm

Maintainer comment pointing to the canonical prompt source file and noting the text is lint-checked for sync. It gives the AI no instructions.

Reviewed by Claude (AI-assisted review), 2026-11-21

injection.html-comment: Hidden instruction in an HTML comment med

agents/editorial_synthesizer_agent.md:60

OWASP LLM LLM01 Prompt InjectionOWASP Agentic ASI01 Agent Goal HijackMITRE ATLAS AML.T0051.001 LLM Prompt Injection: IndirectMITRE ATLAS AML.T0068 LLM Prompt ObfuscationCWE CWE-1427 Improper Neutralization of Input Used for LLM Prompting

<!-- Canonical inline-prompt source: ../references/reviewer_sprint_prompt_source.md. This whole-file-dispatched protocol stays inline and is byte-sync-linted; the pointer is not a runtime include. -->

What this means: HTML comments are invisible when a document is rendered but are still read by the AI, so they can carry instructions meant to stay unseen.

The rule's general advice: Read the comment; remove it or do not install. (see the review note for this case)

Known false alarm

Maintainer comment pointing to the canonical prompt source file and noting the text is lint-checked for sync. It gives the AI no instructions.

Reviewed by Claude (AI-assisted review), 2026-11-21

injection.override: Tries to override the AI's instructions high

agents/eic_agent.md:107

OWASP LLM LLM01 Prompt InjectionOWASP LLM LLM07 System Prompt LeakageOWASP Agentic ASI01 Agent Goal HijackMITRE ATLAS AML.T0051.001 LLM Prompt Injection: IndirectMITRE ATLAS AML.T0110.000 AI Agent Tool Poisoning: Definition and InstructionsMITRE ATLAS AML.T0069.002 Discover LLM System Information: System PromptCWE CWE-1427 Improper Neutralization of Input Used for LLM Prompting

ignore prior instructions

What this means: Text read by the AI that says to ignore earlier instructions, reveal the system prompt or hide things from you is a classic prompt-injection attempt.

The rule's general advice: Do not install; the text is trying to steer the assistant against you. (see the review note for this case)

Known false alarm

The phrase appears inside an instruction telling the reviewer agent to treat the manuscript and its own earlier output as data, and to ignore embedded lines such as "ignore previous instructions". It is a defence against prompt injection.

Reviewed by Claude (AI-assisted review), 2026-11-21

injection.html-comment: Hidden instruction in an HTML comment med

agents/eic_agent.md:37

OWASP LLM LLM01 Prompt InjectionOWASP Agentic ASI01 Agent Goal HijackMITRE ATLAS AML.T0051.001 LLM Prompt Injection: IndirectMITRE ATLAS AML.T0068 LLM Prompt ObfuscationCWE CWE-1427 Improper Neutralization of Input Used for LLM Prompting

<!-- Canonical inline-prompt source: ../references/reviewer_sprint_prompt_source.md. The dispatched H3 bodies stay inline and are byte-sync-linted; this pointer is not a runtime include. -->

What this means: HTML comments are invisible when a document is rendered but are still read by the AI, so they can carry instructions meant to stay unseen.

The rule's general advice: Read the comment; remove it or do not install. (see the review note for this case)

Known false alarm

Maintainer comment pointing to the canonical prompt source file and noting the text is lint-checked for sync. It gives the AI no instructions.

Reviewed by Claude (AI-assisted review), 2026-11-21

injection.override: Tries to override the AI's instructions high

agents/methodology_reviewer_agent.md:104

OWASP LLM LLM01 Prompt InjectionOWASP LLM LLM07 System Prompt LeakageOWASP Agentic ASI01 Agent Goal HijackMITRE ATLAS AML.T0051.001 LLM Prompt Injection: IndirectMITRE ATLAS AML.T0110.000 AI Agent Tool Poisoning: Definition and InstructionsMITRE ATLAS AML.T0069.002 Discover LLM System Information: System PromptCWE CWE-1427 Improper Neutralization of Input Used for LLM Prompting

ignore previous instructions

What this means: Text read by the AI that says to ignore earlier instructions, reveal the system prompt or hide things from you is a classic prompt-injection attempt.

The rule's general advice: Do not install; the text is trying to steer the assistant against you. (see the review note for this case)

Known false alarm

The phrase appears inside an instruction telling the reviewer agent to treat the manuscript and its own earlier output as data, and to ignore embedded lines such as "ignore previous instructions". It is a defence against prompt injection.

Reviewed by Claude (AI-assisted review), 2026-11-21

injection.html-comment: Hidden instruction in an HTML comment med

agents/methodology_reviewer_agent.md:38

OWASP LLM LLM01 Prompt InjectionOWASP Agentic ASI01 Agent Goal HijackMITRE ATLAS AML.T0051.001 LLM Prompt Injection: IndirectMITRE ATLAS AML.T0068 LLM Prompt ObfuscationCWE CWE-1427 Improper Neutralization of Input Used for LLM Prompting

<!-- Canonical inline-prompt source: ../references/reviewer_sprint_prompt_source.md. The dispatched H3 bodies stay inline and are byte-sync-linted; this pointer is not a runtime include. -->

What this means: HTML comments are invisible when a document is rendered but are still read by the AI, so they can carry instructions meant to stay unseen.

The rule's general advice: Read the comment; remove it or do not install. (see the review note for this case)

Known false alarm

Maintainer comment pointing to the canonical prompt source file and noting the text is lint-checked for sync. It gives the AI no instructions.

Reviewed by Claude (AI-assisted review), 2026-11-21

injection.override: Tries to override the AI's instructions high

agents/perspective_reviewer_agent.md:108

OWASP LLM LLM01 Prompt InjectionOWASP LLM LLM07 System Prompt LeakageOWASP Agentic ASI01 Agent Goal HijackMITRE ATLAS AML.T0051.001 LLM Prompt Injection: IndirectMITRE ATLAS AML.T0110.000 AI Agent Tool Poisoning: Definition and InstructionsMITRE ATLAS AML.T0069.002 Discover LLM System Information: System PromptCWE CWE-1427 Improper Neutralization of Input Used for LLM Prompting

ignore prior instructions

What this means: Text read by the AI that says to ignore earlier instructions, reveal the system prompt or hide things from you is a classic prompt-injection attempt.

The rule's general advice: Do not install; the text is trying to steer the assistant against you. (see the review note for this case)

Known false alarm

The phrase appears inside an instruction telling the reviewer agent to treat the manuscript and its own earlier output as data, and to ignore embedded lines such as "ignore previous instructions". It is a defence against prompt injection.

Reviewed by Claude (AI-assisted review), 2026-11-21

injection.html-comment: Hidden instruction in an HTML comment med

agents/perspective_reviewer_agent.md:38

OWASP LLM LLM01 Prompt InjectionOWASP Agentic ASI01 Agent Goal HijackMITRE ATLAS AML.T0051.001 LLM Prompt Injection: IndirectMITRE ATLAS AML.T0068 LLM Prompt ObfuscationCWE CWE-1427 Improper Neutralization of Input Used for LLM Prompting

<!-- Canonical inline-prompt source: ../references/reviewer_sprint_prompt_source.md. The dispatched H3 bodies stay inline and are byte-sync-linted; this pointer is not a runtime include. -->

What this means: HTML comments are invisible when a document is rendered but are still read by the AI, so they can carry instructions meant to stay unseen.

The rule's general advice: Read the comment; remove it or do not install. (see the review note for this case)

Known false alarm

Maintainer comment pointing to the canonical prompt source file and noting the text is lint-checked for sync. It gives the AI no instructions.

Reviewed by Claude (AI-assisted review), 2026-11-21

Dispute this result

Maintainer and think this is wrong? Open a dispute on GitHub with the target id skill-imbad0202-academic-research-skills-academic-paper-reviewer-9f6315.