Caveat verdict

12321-harass-report

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

Both reads and writes files

The skill automates a reporting process to 12321.cn, which involves executing JavaScript and potentially interacting with external systems, raising some risk.

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.

78
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 medium

Both reads and writes files — verify scope is limited to intended directories

LLM06 · ASI02

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read+write

Permissions & capabilities

No declared permissions — minimal attack surface.

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