omh-github-issue-intake

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted public chat reports to generate GitHub issues, which represents an ingestion surface for potential indirect prompt injection attacks.
  • Ingestion points: The skill explicitly processes "public report or summary" and user-provided inputs as part of the issue intake workflow in SKILL.md.
  • Boundary markers: The skill requires an "evidence boundary", a "direction check", and "explicit confirmation" from the user before any action is taken.
  • Capability inventory: The skill facilitates repository exploration, duplicate searching, and the preparation of issue packages to be handed off to an authorized connector.
  • Sanitization: The instructions include strict safety rules prohibiting mutations to code or settings and mandate that security vulnerability reports be redirected to private channels.
  • [COMMAND_EXECUTION]: The documentation contains a shell command snippet used for recording the skill's execution status.
  • Evidence: omh runtime record --skill github-issue-intake --harness github-issue-intake --status started
  • Context: This command is intended for platform-level telemetry and status tracking and does not interpolate untrusted external data into the execution string.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:33 PM
Security Audit — agent-trust-hub — omh-github-issue-intake