create-github-issues-for-unmet-specification-requirements

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from specification files and the codebase to generate GitHub issues, creating an attack surface for indirect prompt injection.
  • Ingestion points: Specification files referenced by ${file} and found in the /spec/ directory.
  • Boundary markers: Absent; there are no instructions to the agent to disregard instructions found within the data files.
  • Capability inventory: Reading local files and using GitHub tools create_issue and search_issues.
  • Sanitization: Absent; the skill does not mention validation or sanitization of the requirement content before it is used to populate GitHub issues.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:50 AM