Caveat verdict

clawdraw

claw-draw

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill uses an API key for its operation, which could be a concern if not properly secured.

⚠ 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.

30
security
100
transparency
100
maintenance

Findings (6)

Pattern match high

Uses eval() — can execute arbitrary code

references/SECURITY.md · prose · downgraded · eval(

Pattern match high

Pipe to python — executes piped content as Python code

community/parallel-swarm-demo.sh · prose · downgraded · | python3

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("API key") and emits it outward ("insert"). 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 · | Action | Command | |--------|---------| | **First-Time Setup** | `clawdraw setup` — create agent + save API key (npm users) | | **Link Account** | `clawdraw l

Pattern match medium

Opens WebSocket connection

README.md · code · WebSocket

Pattern match medium

References child_process — can spawn system processes

references/SECURITY.md · prose · downgraded · child_process

Pattern match medium

Base64 encoding/decoding

references/WEBSOCKET.md · code · base64-encode

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: CLAWDRAW_API_KEY). Requires 1 system binary.

network_incredential_accessdata_encoding

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API