pf-code-review

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it is designed to ingest and analyze external code files which could contain adversarial instructions.
  • Ingestion points: The skill uses Read, Glob, and Grep tools to access project files.
  • Boundary markers: No explicit delimiters are used to separate instructions from the data being reviewed.
  • Capability inventory: The agent is limited to read-only access to the file system and providing text feedback.
  • Sanitization: There is no evidence of input validation or sanitization for the code content being analyzed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 04:28 PM