user-story-implementer

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) and git to manage issues, branches, and pull requests. It also executes a local helper script (scripts/create_pr.sh) to format and submit pull requests. These actions are primary functions of the skill and are performed using standard authentication and workflow patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes content from GitHub issues and pull request comments.
  • Ingestion points: Untrusted data enters the agent context via gh issue view and gh pr view --comments as specified in the SKILL.md workflow.
  • Boundary markers: None. The agent is instructed to directly extract acceptance criteria and review comments from the fetched external data.
  • Capability inventory: The agent has the ability to modify local files, commit changes, and interact with the remote repository via the GitHub CLI.
  • Sanitization: The skill does not perform sanitization or validation on the content fetched from GitHub before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 05:43 AM
Security Audit — agent-trust-hub — user-story-implementer