performance-review-writer
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is focused on a legitimate productivity use case and contains no evidence of malicious intent or hidden behaviors.- [SAFE]: Privacy safeguards are explicitly included in the instructions, requiring the agent to redact sensitive personal details, attendee lists, and raw excerpts from processed communications.- [SAFE]: The skill instructions restrict output to local workspace directories (the
outputs/folder) and do not contain any network operations or tools that would enable external data exfiltration.- [SAFE]: No obfuscation, prompt injection attempts, or unauthorized privilege escalation commands were found in the skill's instructions or metadata.
Audit Metadata