github-issue-flow

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes content from GitHub Issues and Pull Requests, which are external sources that could contain adversarial instructions designed to influence agent behavior.
  • Ingestion points: The skill fetches external data using gh issue view, gh pr list, and gh api to read issue bodies, comments, and timelines (references/issue-workflow.md).
  • Boundary markers: There are no explicit instructions or delimiters used to separate the external data from the skill's core logic to prevent the agent from following instructions embedded in the external content.
  • Capability inventory: The skill has the capability to execute shell commands (pnpm test, pnpm lint), perform Git operations (git push, git worktree), and create GitHub resources (gh issue create, gh pr create).
  • Sanitization: No validation or filtering is applied to the content retrieved from GitHub before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill relies on the execution of shell commands through the GitHub CLI (gh), Git, and project-specific build tools (pnpm) to automate the triage, implementation, and verification phases of the workflow (SKILL.md, references/issue-workflow.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 01:23 AM
Security Audit — agent-trust-hub — github-issue-flow