ClawAudit verdict
clawsec-bak
Identical to clawsec/clawsec-1-0-0: all dangerous-looking strings are detection rule table entries for the proxy to catch, not instructions to the agent to perform those actions.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (13)
Accesses sensitive system files
SKILL.md · prose · downgraded · /etc/passwd
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · prose · downgraded · curl <url> \| bash
Pipe-to-shell pattern (wget | sh)
SKILL.md · prose · downgraded · wget <url> \| sh
Recursive delete from root or home — destructive command
SKILL.md · prose · downgraded · rm -rf /
Pipe to bash — executes piped content as shell commands
SKILL.md · prose · downgraded · | bash
Pipe to sh — executes piped content as shell commands
SKILL.md · prose · downgraded · | sh
References sudo — requests elevated privileges
SKILL.md · code · sudo
Accesses system credential store
SKILL.md · code · Keychain
HTTP request to bare IP address — common in malicious payloads
SKILL.md · code · http://127.0.0.1
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | Python
Possible prompt injection — attempts to redefine agent identity
SKILL.md · prose · downgraded · You are now
References SSH/GPG private keys
SKILL.md · prose · downgraded · ssh_key
Accesses .ssh directory
SKILL.md · prose · downgraded · .ssh/
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_store Is this flag fair?
Thanks — recorded.