swarm-review

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions define a legitimate process for multi-perspective code reviews using well-known development tools like the GitHub CLI.
  • [PROMPT_INJECTION]: The skill processes untrusted input from pull request diffs and commit history (SKILL.md). While this represents a surface for indirect prompt injection, it is inherent to the tool's primary purpose.
  • Ingestion points: Pull request diffs and commit data fetched via gh pr diff and gh pr view (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Write operations via gh pr review and gh pr comment (SKILL.md).
  • Sanitization: Absent; the skill relies on the agent's default safety filtering when processing the diff content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 10:41 PM
Security Audit — agent-trust-hub — swarm-review