ClawAudit verdict
skill-evolver
adaptive-skill-evolver
The skill contains executionSinkDetected=true and credential_access, which indicates potential malicious behavior.
⚠ 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 (5)
Writes to SKILL.md — self-modifying skill
SKILL.md · code · SKILL.md inline write
References child_process — can spawn system processes
scripts/lib/llm-client.js · prose · downgraded · child_process
Node http/https module — low-level network access
scripts/lib/llm-client.js · prose · downgraded · require('http')
Accesses sensitive environment variables
scripts/lib/llm-client.js · prose · downgraded · process.env.EVOLVER_API_KEY
Popular HTTP library — network access
scripts/lib/llm-client.js · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 system binary.
network_incredential_access Is this flag fair?
Thanks — recorded.