Caveat verdict

bigmodel-image-video

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

Accesses credentials AND writes files

This skill generates images and videos via the BigModel (Zhipu AI) API using a user-supplied BIGMODEL_API_KEY; all capabilities (file_write for saving outputs, credential_access for the API key, network calls to open.bigmodel.cn) align with the legitimate image/video generation purpose.

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.

20
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 writes files — may persist stolen credentials locally

LLM02 · LLM06 · ASI03

Capability combination high

Accesses agent memory AND writes files — may modify agent behavior persistently

LLM01 · LLM06 · ASI01 · ASI06

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read+write

Accesses agent memory/configuration files

agent_memory

Findings (2)

Pattern match high

Accesses shell history/config

SKILL.md · code · ~/.zshrc

Pattern match low

Python os.environ.get — reads environment variable

lib/image_video.py · prose · downgraded · os.environ.get(

Why the tier is capped

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

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