issue-sprint

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources (GitHub issues and PRs) that could influence the agent's behavior or be passed to subagents.
  • Ingestion points: External data is ingested via gh issue view, gh pr view, and gh pr diff commands in SKILL.md.
  • Boundary markers: The skill lacks explicit boundary markers or instructions to ignore embedded commands when copying issue bodies into subagent prompts.
  • Capability inventory: The skill possesses the ability to merge PRs (gh pr merge), approve code (gh pr review --approve), and delete branches/worktrees (git worktree remove, git branch -d).
  • Sanitization: There is no evidence of sanitization or validation of the content retrieved from GitHub before it is used in prompts or decision-making.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 06:22 AM