Caveat verdict

image-recognition

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Reads local image files, base64-encodes them, and sends to a user-configured vision model API; the skill reads OpenClaw own config file for the API endpoint, which is the expected integration pattern.

⚠ 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.

0
security
60
transparency
90
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (6)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="sk-sp-xxxxxxxxxxxxx

Pattern match high

subprocess execution — runs system commands from Python

README.md · code · subprocess.run(

Pattern match medium

Accesses OpenClaw config/secrets directly

SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match medium

pip3 install — installs Python packages at runtime

SKILL.md · code · pip3 install

Pattern match medium

POSTs data to external URL

usage-guide.md · code · .post( "https://

Pattern match low

Python os.environ.get — reads environment variable

recognize.py · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class 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_inpackage_installcredential_access

Is this flag fair?

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