Caveat verdict

cleanercat

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

Reads local files AND makes external network calls

The skill downloads a binary from a raw GitHub URL, makes it executable, and then uses Python to modify Claude Code settings.json and installed_plugins.json to register it as a plugin; downloading and auto-registering an unsigned binary that modifies the agent own configuration is a meaningful elevated 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.

0
security
90
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 critical

Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)

LLM02 · LLM06 · ASI03

Capability combination critical

Accesses agent memory/notes AND makes external network calls — may leak personal data

LLM02 · LLM07 · ASI03 · ASI06

Capability combination high

Accesses agent memory AND makes external network calls — may leak conversation history

LLM02 · LLM07 · ASI06

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Performs file operations but does not declare file-accessing binaries

file_read

Accesses agent memory/configuration files

agent_memory

Permissions & capabilities

No declared permissions — minimal attack surface.

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