ClawAudit verdict
raini-skill-audit
Receives external input AND uses eval
Security auditing skill that scans OpenClaw skills for supply chain attack patterns including credential exfiltration, eval usage, and suspicious network calls; the dynamic_eval capability reflects scanning for eval patterns in other skills rather than performing any itself.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)
LLM01 · LLM05 · ASI01 · ASI05
Findings (6)
Uses eval() — can execute arbitrary code
SKILL.md · code · eval(
Uses exec() — may execute shell commands
SKILL.md · prose · downgraded · exec(
References child_process — can spawn system processes
SKILL.md · prose · downgraded · child_process
Accesses .ssh directory
SKILL.md · prose · downgraded · .ssh/
Accesses sensitive environment variables
SKILL.md · prose · downgraded · process.env.API_KEY
Popular HTTP library — network access
src/audit.js · prose · downgraded · axios
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/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.
network_indynamic_eval Thanks — recorded.