differential-review

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill establishes a workflow for analyzing untrusted external data such as pull requests, commits, and diffs, which creates a surface for indirect prompt injection attacks.
  • Ingestion points: The skill is designed to read and process code content from PRs, commit ranges, and git diffs (SKILL.md).
  • Boundary markers: The instructions lack explicit requirements for using delimiters or boundary markers to separate untrusted code content from agent instructions.
  • Capability inventory: The skill has the ability to generate markdown report files and interface with other tools like 'issue-writer' to create formal reports.
  • Sanitization: There are no specific instructions provided for sanitizing or escaping content extracted from code comments or commit messages before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 08:32 PM
Security Audit — agent-trust-hub — differential-review