managing-github-issues
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and process external data from GitHub issues, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: The skill uses
gh issue list(in SKILL.md) to retrieve issue data which is then used to "find work". - Boundary markers: The instructions do not define clear delimiters or use "ignore embedded instructions" warnings when processing issue content.
- Capability inventory: The skill possesses capabilities to create and close issues (
gh issue create,gh issue close). - Sanitization: There is no mention of sanitizing or filtering the content retrieved from GitHub before the agent acts upon it.
Audit Metadata