roo-conflict-resolution

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources.
  • Ingestion points: Pull request titles and descriptions are fetched using gh pr view in SKILL.md (Step 2).
  • Boundary markers: The instructions do not define clear boundaries or provide explicit warnings for the agent to ignore instructions embedded within the PR metadata.
  • Capability inventory: The skill uses high-privilege git operations such as git rebase, git add, and GitHub CLI commands (gh pr checkout).
  • Sanitization: There is no mention of sanitizing or escaping the content retrieved from pull requests before it is analyzed for 'intent'.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 11:46 PM
Security Audit — agent-trust-hub — roo-conflict-resolution