roo-conflict-resolution

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git and gh (GitHub CLI) to manage branches, fetch PR metadata, and resolve conflicts. These are standard operations for the described workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, which could be exploited to influence agent behavior.
  • Ingestion points: Fetches pull request titles and descriptions using gh pr view in SKILL.md.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are used when processing PR metadata.
  • Capability inventory: Uses git and gh for repository management and file modification across the resolution workflow.
  • Sanitization: No sanitization or validation is performed on the ingested PR metadata before it is used for decision-making context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 08:28 AM
Security Audit — agent-trust-hub — roo-conflict-resolution