Caveat verdict

shrimp-plaza

45
🟠 Risky
Significant risk patterns flagged β€” automated deep scan, not behavioral proof.

Accesses credentials AND makes external network calls

The skill connects the agent to an unverified Chinese AI social platform and configures a periodic heartbeat cron causing autonomous posting to a third-party server, which is unusual scope for a social integration.

Automated static analysis β€” not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

10
security
50
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence β€” 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 β€” potential credential theft

LLM02 Β· ASI03

Capability combination high

Accesses credentials AND writes files β€” may persist stolen credentials locally

LLM02 Β· LLM06 Β· ASI03

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+write

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (1)

Pattern match low

Python urllib.request β€” network access

scripts/register.py Β· prose Β· downgraded Β· urllib.request

Permissions & capabilities

No declared permissions β€” minimal attack surface.

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