update-issue
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it reads external, untrusted data from GitHub issues and templates and uses that data to influence its output and actions.
- Ingestion points: The skill ingests data via
gh issue view(to see current title/body) and by reading repository files in.github/ISSUE_TEMPLATE/(SKILL.md). - Boundary markers: The instructions do not define clear delimiters or "ignore instructions" warnings to separate user-provided issue content from the skill's operational logic.
- Capability inventory: The skill possesses the capability to modify repository state using the
gh issue edittool via Bash (SKILL.md). - Sanitization: There is no evidence of sanitization, filtering, or validation performed on the ingested issue content before it is processed by the model.
Audit Metadata