Caveat verdict

test-restaurant-inspection

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

Accesses credentials AND makes external network calls

Uses EZVIZ camera credentials to capture images and call Ezviz AI analysis for restaurant safety inspection; all calls go to the expected Ezviz platform.

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.

23
security
50
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (2)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · SECRET="your_app_secret

Pattern match low

Python os.getenv — reads environment variable

scripts/restaurant_inspection.py · prose · downgraded · os.getenv(

Permissions & capabilities

Requires 3 environment variables. (1 sensitive: EZVIZ_APP_SECRET).

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