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