openclaw
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, 1× · first at skills/agent-cost-report/scripts/acr/transcripts.py:19)exfil.host: References an exfiltration-style host (high, 1× · first at src/index.ts:541)fetch.unsafe-entry: Archive or repo contains an unsafe entry (high, 2× · first at skills/make-plan/SKILL.md)remote-code.pipe-shell: Pipes a download into a shell (high, 1× · first at install.sh:412)
- Kind
- Skill
- Source
- github
- Repository
- thedotmack/claude-mem / openclaw
- Commit
c0f37d60b2e4860851575e3cbb003f23fc340d4e- Popularity
- 118,537 GitHub stars (2026-11-20)
- Link
- https://github.com/thedotmack/claude-mem/tree/c0f37d60b2e4860851575e3cbb003f23fc340d4e/openclaw
- Scanned
- 2026-11-20T22:39:04+00:00
- Scan time
- 5.9 s
- Scanned as
- skill
Review note: Flags are in-repo symlinks, a documented Bun install, an opt-in cost-report skill and a user-configured Telegram feed; nothing hidden.
Findings (5)
fetch.unsafe-entry: Archive or repo contains an unsafe entry high
skills/make-plan/SKILL.md
CWE CWE-22 Improper Limitation of a Pathname to a Restricted DirectoryCWE CWE-59 Improper Link Resolution Before File AccessCWE CWE-409 Improper Handling of Highly Compressed Data (Data Amplification)
symlink skills/make-plan/SKILL.md points outside the target root
What this means: Path traversal, absolute paths, links pointing outside the package, or oversized archives are used to overwrite files or exhaust disk during extraction.
The rule's general advice: Do not install; the unsafe entries were skipped during scanning. (see the review note for this case)
Known false alarm
skills/do/SKILL.md and skills/make-plan/SKILL.md are symlinks to ../../../plugin/skills/..., the same skills in the parent claude-mem repo. They leave the openclaw subfolder but stay inside the pinned repository, and the target files are ordinary SKILL.md files.
Reviewed by Claude (AI-assisted review), 2026-11-21
fetch.unsafe-entry: Archive or repo contains an unsafe entry high
skills/do/SKILL.md
CWE CWE-22 Improper Limitation of a Pathname to a Restricted DirectoryCWE CWE-59 Improper Link Resolution Before File AccessCWE CWE-409 Improper Handling of Highly Compressed Data (Data Amplification)
symlink skills/do/SKILL.md points outside the target root
What this means: Path traversal, absolute paths, links pointing outside the package, or oversized archives are used to overwrite files or exhaust disk during extraction.
The rule's general advice: Do not install; the unsafe entries were skipped during scanning. (see the review note for this case)
Known false alarm
skills/do/SKILL.md and skills/make-plan/SKILL.md are symlinks to ../../../plugin/skills/..., the same skills in the parent claude-mem repo. They leave the openclaw subfolder but stay inside the pinned repository, and the target files are ordinary SKILL.md files.
Reviewed by Claude (AI-assisted review), 2026-11-21
remote-code.pipe-shell: Pipes a download into a shell high
install.sh:412
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesOWASP Agentic ASI05 Unexpected Code Execution (RCE)MITRE ATLAS AML.T0050 Command and Scripting InterpreterCWE CWE-494 Download of Code Without Integrity Check
if ! curl -fsSL https://bun.sh/install | bash; then
What this means: Executes whatever the remote server returns, unreviewed.
The rule's general advice: Download, verify a checksum, then run. (see the review note for this case)
Expected for what this tool does
The installer runs Bun's official installer (curl https://bun.sh/install | bash) only when Bun is missing or too old, and prints what it is doing. This is a standard, visible dependency install.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
skills/agent-cost-report/scripts/acr/transcripts.py:19
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
CLAUDE_GLOB = os.path.join("~", ".claude", "projects", "**", "*.jsonl")
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
The agent-cost-report skill reads local Claude/Codex transcripts to build a cost report, which is its stated purpose. Its only network use is an optional OpenRouter classifier, off by default (--classify), that sends scrubbed excerpts of at most 1,500 characters using the user's own key, as SKILL.md documents.
Reviewed by Claude (AI-assisted review), 2026-11-21
exfil.host: References an exfiltration-style host high
src/index.ts:541
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0025 Exfiltration via Cyber Means
const response = await fetch(`https://api.telegram.org/bot${botToken}/sendMessage`, {
What this means: Paste, webhook and tunnel services are commonly used to receive stolen data.
The rule's general advice: Remove or justify the destination. (see the review note for this case)
Expected for what this tool does
Sends observation-feed messages straight to the Telegram Bot API, using a bot token and chat id the user puts in the plugin's feed config. This is the documented channel-feed feature.
Reviewed by Claude (AI-assisted review), 2026-11-21
2 low-severity notes (informational, do not affect the result)
install-dir-access: Reads or writes Claude's install folders low
install.sh:1098
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
"${HOME}/.claude/plugins/marketplaces/thedotmack"
What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.
What you can do: Check which files it adds there and that you want them.
install-dir-access: Reads or writes Claude's install folders low
skills/agent-cost-report/scripts/acr/transcripts.py:35
MITRE ATLAS AML.T0081 Modify AI Agent Configuration
"""Project dir = path segment after `/.claude/projects/` (parse_transcripts.py:20).
What this means: Uses ~/.claude/agents, skills, commands or plugins (or a project .claude/ folder). Normal for installers, but it changes what Claude loads.
What you can do: Check which files it adds there and that you want them.
Dispute this result
Maintainer and think this is wrong? Open a dispute on GitHub with the target id skill-thedotmack-claude-mem-openclaw-493648.