Caveat verdict
adeptloop-improve
adeptloop-improve scores 75/100 (Caution). It requires 1 env vars. 1 undeclared capability detected — the skill does more than its permissions suggest. 1 high-severity flag.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
file_read
Findings (2)
Instruction-prose smuggling shape detected: collects a sensitive target ("api_key") and emits it outward ("POST"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.
SKILL.md · 1. Read the `diff`, `target_file`, and `rollback_instructions` from the recommendation. If not already fetched, call `GET https://www.adeptloop.com/api/v1/recom
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/.env
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: ADEPTLOOP_API_KEY).
credential_accessnetwork_infile_read Is this flag fair?
Thanks — recorded.