gt-plan-issue
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from Forgejo issue descriptions and comments, which could contain malicious instructions designed to manipulate the agent's behavior.
- Ingestion points: The output from the
gt issue view <issue-id> --commentscommand (found in SKILL.md) is read directly into the agent's context. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to isolate the fetched issue content from its own operational logic.
- Capability inventory: While the skill focuses on planning, it operates in an environment where the agent likely has tools for file modification or command execution that could be targeted by instructions embedded in the data.
- Sanitization: The skill does not implement any filtering or sanitization of the content retrieved from the external source.
Audit Metadata