ClawAudit verdict
codealive-context-engine
Skill sends code search queries and codebase content to an external CodeAlive API service; while this is the stated purpose, it involves transmitting potentially sensitive code to a third-party server.
⚠ 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.
Permission integrity
credential_access
Findings (7)
Possible hardcoded credential
SKILL.md · code · API_KEY="your_key_here
Accesses system credential store
SKILL.md · prose · downgraded · Keychain
Popular HTTP library — network access
references/query-patterns.md · code · Axios
subprocess execution — runs system commands from Python
scripts/lib/api_client.py · prose · downgraded · subprocess.run(
Accesses shell history/config
setup.py · prose · downgraded · ~/.zshrc
Python urllib.request — network access
scripts/lib/api_client.py · prose · downgraded · urllib.request
Python os.getenv — reads environment variable
scripts/lib/api_client.py · prose · downgraded · os.getenv(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). 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_access Is this flag fair?
Thanks — recorded.