skill-review

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes uncommitted code changes that may contain adversarial instructions.
  • Ingestion points: Content from SKILL.md, README.md, and reference files is read into the agent's context using the Read tool and git diff commands.
  • Boundary markers: There are no delimiters or specific instructions to treat the file content as passive data, allowing embedded instructions to potentially influence the agent's logic.
  • Capability inventory: The agent has the authority to modify files using the Edit tool and execute git commands via Bash.
  • Sanitization: No content validation or sanitization is performed on the ingested data before it is passed to the review process.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 01:38 AM