Caveat verdict

baidu-content-censor

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

Accesses credentials AND encodes data

Baidu content moderation skill sending user-provided text/images to aip.baidubce.com for censor analysis using AK/SK credentials from environment variables; stated purpose is content safety detection.

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.

58
security
30
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 encodes data — may obfuscate stolen credentials

LLM02 · ASI03 · ASI04

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (1)

Pattern match low

Python os.environ.get — reads environment variable

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

Permissions & capabilities

No declared permissions — minimal attack surface.

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