cisco-ai-mcp-scanner
Not malicious, needs a look Reviewed: expected behaviour
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:
credential-access: Touches credentials or secrets (high, 6× · first at mcpscanner/server.py:20)
- Kind
- MCP server
- Source
- pypi
- Version
4.8.7- Popularity
- 42,578 PyPI downloads/week (2026-11-20)
- Link
- https://pypi.org/project/cisco-ai-mcp-scanner/4.8.7/
- Scanned
- 2026-11-20T22:15:42+00:00
- Scan time
- 8.8 s
Review note: A security scanner whose flags are its own YARA rules, file-type lists and documented LLM/VirusTotal settings.
Findings (7)
credential-access: Touches credentials or secrets high
mcpscanner/server.py:20
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
Configuration is loaded from a .env file or environment variables.
What this means: Reads files or environment holding keys, tokens or sessions.
The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)
Known false alarm
A module docstring saying configuration comes from a .env file or environment variables.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
mcpscanner/config/config.py:87
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
aws_profile_name (str, optional): AWS profile name from ~/.aws/credentials. Falls back to AWS_PROFILE env var.
What this means: Reads files or environment holding keys, tokens or sessions.
The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)
Expected for what this tool does
Docstring for the optional AWS Bedrock LLM settings, which can use an AWS profile from ~/.aws/credentials. That is how the user picks Bedrock as the analysis model.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
mcpscanner/config/constants.py:103
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
DEFAULT_ENV_FILE: str = os.getenv("MCP_SCANNER_DEFAULT_ENV_FILE", ".env")
What this means: Reads files or environment holding keys, tokens or sessions.
The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)
Expected for what this tool does
Sets the default .env file the scanner loads its own settings from (overridable through MCP_SCANNER_DEFAULT_ENV_FILE).
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
mcpscanner/core/analyzers/virustotal_analyzer.py:64
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
".env.example", ".dockerignore", # templates
What this means: Reads files or environment holding keys, tokens or sessions.
The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)
Known false alarm
'.env.example' is in a list of plain-text file extensions that the VirusTotal analyzer skips. Uploading unknown files to VirusTotal is off by default (upload_files=False) and needs a VIRUSTOTAL_API_KEY.
Reviewed by Claude (AI-assisted review), 2026-11-21
exfil.combo: Reads credentials and makes network calls med
mcpscanner/core/analyzers/virustotal_analyzer.py:64
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0037 Data from Local SystemMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0025 Exfiltration via Cyber Means
".env.example", ".dockerignore", # templates
What this means: Credential access together with outbound requests in one file is the shape of data theft.
The rule's general advice: Do not install unless the flow is understood and benign. (see the review note for this case)
Known false alarm
'.env.example' is in a list of plain-text file extensions that the VirusTotal analyzer skips. Uploading unknown files to VirusTotal is off by default (upload_files=False) and needs a VIRUSTOTAL_API_KEY.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
mcpscanner/data/yara_rules/credential_harvesting.yara:64
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
$env_access_methods = /\b(process\.env\.|os\.environ|getenv\s*\()/
What this means: Reads files or environment holding keys, tokens or sessions.
The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)
Known false alarm
Detection patterns inside the scanner's own YARA rules that look for environment access in scanned code. They are signatures, not code that reads anything.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
mcpscanner/data/yara_rules/system_manipulation.yara:17
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
$sys_env_access = /(\$(PATH|HOME|USER|SHELL|PWD)|process\.env|os\.environ|getenv\s*\()/i
What this means: Reads files or environment holding keys, tokens or sessions.
The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)
Known false alarm
Detection patterns inside the scanner's own YARA rules that look for environment access in scanned code. They are signatures, not code that reads anything.
Reviewed by Claude (AI-assisted review), 2026-11-21
6 low-severity notes (informational, do not affect the result)
credential-access: Touches credentials or secrets low
mcpscanner/cli.py:59
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
What this means: Reads files or environment holding keys, tokens or sessions.
What you can do: Confirm the tool needs this; otherwise do not install.
credential-access: Touches credentials or secrets low
mcpscanner/api/api.py:24
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
What this means: Reads files or environment holding keys, tokens or sessions.
What you can do: Confirm the tool needs this; otherwise do not install.
credential-access: Touches credentials or secrets low
mcpscanner/utils/command_utils.py:79
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
old_environ = dict(os.environ)
What this means: Reads files or environment holding keys, tokens or sessions.
What you can do: Confirm the tool needs this; otherwise do not install.
exfil.host: References an exfiltration-style host low
tests/test_schema_reference_analyzer.py:28
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0025 Exfiltration via Cyber Means
("http://169.254.169.254/latest/meta-data", "private-network", "HIGH"),
What this means: Paste, webhook and tunnel services are commonly used to receive stolen data.
What you can do: Remove or justify the destination.
credential-access: Touches credentials or secrets low
tests/test_server.py:93
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
with tempfile.NamedTemporaryFile(mode="w", suffix=".env", delete=False) as f:
What this means: Reads files or environment holding keys, tokens or sessions.
What you can do: Confirm the tool needs this; otherwise do not install.
credential-access: Touches credentials or secrets low
tests/test_yara_rules_coverage.py:57
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
matching patterns (*.env, *.pem, *.key, *credentials*, *secret*) to
What this means: Reads files or environment holding keys, tokens or sessions.
What you can do: Confirm the tool needs this; otherwise do not install.
Dispute this result
Maintainer and think this is wrong? Open a dispute on GitHub with the target id mcp-pypi-cisco-ai-mcp-scanner-f84fe3.