issue-management
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data by reading GitHub issue content via the
gh issue viewcommand, which could be exploited for indirect prompt injection. - Ingestion points: Data enters the agent context through the output of
gh issue view <number>commands mentioned inSKILL.md. - Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions contained within the fetched issue data.
- Capability inventory: The skill allows the agent to create and modify issues using
gh issue createandgh issue edit. - Sanitization: The skill does not provide methods for sanitizing or validating the data retrieved from GitHub before processing it.
Audit Metadata