fpf-review

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a quality gate for AI sessions, guiding the agent through a checklist of creative and assurance steps. It does not contain any prompt injection, obfuscation, or remote code execution patterns.
  • [COMMAND_EXECUTION]: The skill involves basic file system operations such as writing to .fpf/anomalies/ and .fpf/worklog/, and deleting a sentinel file .fpf/.session-active. These operations are used for workflow state management and session logging, and do not involve executing external binaries or sensitive system commands.
  • [DATA_EXPOSURE]: No hardcoded credentials or access to sensitive system paths (like SSH keys or environment secrets) were detected. The data handled is limited to project-specific logs and process improvement records.
  • [PROMPT_INJECTION]: The instructions are purely procedural and do not attempt to bypass safety filters or override system-level constraints. The use of 'MUST invoke' is a workflow requirement for the agent, not a malicious override.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 07:13 PM