Caveat verdict

ERNIE文生图 百度AI图片生成

ernie-image-gen

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

Text-to-image generation skill using Baidu AI Studio ERNIE-Image with user-provided API key; executionSinkDetected is from documented script invocations and the skill explicitly prohibits sending credentials or sensitive data in prompts.

⚠ 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.

65
security
70
transparency
70
maintenance

Findings (3)

Pattern match critical

Possible hardcoded credential

references/api-guide.md · code · API_KEY="your_access_token_here

Pattern match low

Python urllib.request — network access

scripts/generate.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

scripts/generate.py · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A). 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.

Is this flag fair?

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