Caveat verdict

china-image-gen

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

Accesses credentials AND makes external network calls

Image generation via SiliconFlow API using user-provided SILICONFLOW_API_KEY; sends only user-specified prompts to api.siliconflow.cn, which is the documented, named service for this 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.

0
security
70
transparency
90
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

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (4)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="sk-xxxxxxxxxxxxxxxx

Pattern match critical

Pipe-to-python pattern — remote code execution risk

SKILL.md · code · curl -s ... | python

Pattern match critical

Pipe to python — executes piped content as Python code

SKILL.md · code · | python3

Pattern match high

Accesses OpenClaw config/secrets directly

SKILL.md · code · ~/.openclaw/.env

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class C). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 1 system binary. (1 elevated: curl).

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