resolve-pr-parallel

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing external PR comments as instructions for sub-agents.
  • Ingestion points: PR comment bodies are fetched by scripts/get-pr-comments and passed to pr-comment-resolver agents in Step 3 of SKILL.md.
  • Boundary markers: No delimiters or instructions to ignore embedded commands are present in the workflow description in SKILL.md.
  • Capability inventory: The skill and its sub-agents have capabilities for Bash(gh), Bash(git), and file system access to modify code as defined in SKILL.md.
  • Sanitization: No validation or sanitization is performed on the comment content before it influences agent behavior.
  • [COMMAND_EXECUTION]: Executes GitHub CLI (gh) and git commands to interact with pull requests and repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 11:13 AM