Caveat verdict

visual-muse

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

ComfyUI image generation skill that sends prompts to a user-configured ComfyUI instance (defaulting to localhost); image generation happens locally or at a user-configured endpoint.

⚠ 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.

0
security
100
transparency
90
maintenance

Findings (7)

Pattern match critical

Pipe to bash — executes piped content as shell commands

resources/SOUL.md · code · | bash

Pattern match critical

Recursive delete from root or home — destructive command

TROUBLESHOOTING.md · code · rm -rf ~

Pattern match high

Pipe to python — executes piped content as Python code

tools/paint-dispatch.sh · prose · downgraded · | python3

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

SKILL.md · prose · downgraded · http://127.0.0.1

Pattern match low

Python urllib.request — network access

tools/comfyui-client.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

tools/comfyui-client.py · prose · downgraded · os.environ.get(

Pattern match low

References agent memory files

TROUBLESHOOTING.md · prose · downgraded · MEMORY.md

Why the tier is capped

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

Permissions & capabilities

Requires 1 environment variable. Requires 2 system binaries. (1 elevated: curl).

Is this flag fair?

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