ClawAudit verdict
auto-drive
auto-drive-jim
This skill provides upload/download functionality to the Autonomys decentralized storage network and agent memory chaining; the API key is used transparently for the skill's stated storage purpose, and there is no evidence of credential exfiltration or deceptive 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 (7)
Possible hardcoded credential
references/autodrive-api.md · code · apiKey: 'your-key
Instruction-prose smuggling shape detected: collects a sensitive target ("API key") and emits it outward ("paste"). 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. Navigate to **https://explorer.ai3.storage** (not `ai3.storage` — that's just the landing page) 2. Check authentication: if the sidebar shows a "Log In" butt
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/.env
References sudo — requests elevated privileges
scripts/_lib.sh · prose · downgraded · sudo
References agent memory files
SKILL.md · prose · downgraded · MEMORY.md
Sets world-executable permissions
scripts/_lib.sh · prose · downgraded · chmod 700
Popular HTTP library — network access
scripts/autodrive-recall-chain.sh · 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 environment variable. (1 sensitive: AUTO_DRIVE_API_KEY). Requires 3 system binaries. (1 elevated: curl).
Is this flag fair?
Thanks — recorded.