verify-issue

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process content from GitHub issues and pull requests, which are untrusted external sources.
  • Ingestion points: Data enters the context via gh issue view, gh pr list, and gh issue list commands in SKILL.md.
  • Boundary markers: The skill does not utilize delimiters or specific instructions to ignore embedded agent directives within the fetched issue bodies.
  • Capability inventory: The agent has access to repository files (Read/Grep/Glob), GitHub CLI (gh), and git commands.
  • Sanitization: Content from GitHub is processed directly without filtering or sanitization of potential prompt injection patterns.
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) and git to interact with the environment. It also employs dynamic context injection (!command) to retrieve the repository's name and default branch automatically during initialization. These commands are localized to the current environment and do not involve remote code execution from untrusted sources.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 02:20 AM
Security Audit — agent-trust-hub — verify-issue