gt-get-issue
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external source (Forgejo issue descriptions and comments) which could contain malicious prompts designed to manipulate the agent's behavior.
- Ingestion points: External data is retrieved via the
gt issue view <issue-id> --commentscommand as described inSKILL.md. - Boundary markers: Absent. There are no instructions to use delimiters or ignore embedded instructions when processing the output from the issue tracker.
- Capability inventory: The skill uses the
gtCLI tool for reading information; no write or execution capabilities are explicitly defined within this specific skill file. - Sanitization: Absent. The skill does not provide instructions for sanitizing or escaping the retrieved issue content before summarization.
Audit Metadata