Caveat verdict
going-on-a-date
Accesses credentials AND makes external network calls
Meetup sync skill using the AILove agent API; explicitly states it does not expose counterpart privacy and makes only two documented API endpoints, with credentials stored locally at 600 permissions.
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.
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.
Accesses credentials AND makes external network calls β potential credential theft
LLM02 Β· ASI03
Permission integrity
network_out
credential_access
Findings (1)
Instructs covert action β may act without user awareness
SKILL.md Β· prose Β· downgraded Β· silently
Permissions & capabilities
No declared permissions β minimal attack surface.
network_outcredential_access Thanks β recorded.