access
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a secure design by managing state through local JSON files instead of direct API interactions, which minimizes the external attack surface.
- [SAFE]: It contains explicit, high-quality security instructions to mitigate prompt injection by directing the agent to ignore any access requests originating from untrusted external sources like Discord or Telegram messages.
- [SAFE]: The skill enforces manual user intervention and specific code verification for pairing requests, preventing attackers from tricking the agent into auto-approving malicious access entries.
- [SAFE]: File operations and directory creation are scoped to the user's local application configuration directory, and no network exfiltration or remote code execution capabilities were detected.
Audit Metadata