plan-feature-from-issue
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from GitHub issues to generate project planning artifacts.
- Ingestion points: The agent retrieves the issue title, body, and comments using the
gh issue viewcommand as described in Step 0. - Boundary markers: There are no instructions to wrap the retrieved issue content in delimiters or to provide the agent with explicit instructions to ignore any hidden commands or system instructions within the issue body.
- Capability inventory: The skill's capabilities are limited to reading project templates and roadmap files, and writing SPEC documents and roadmap updates. It does not have access to execute arbitrary code or perform unauthorized network operations.
- Sanitization: The skill does not specify any sanitization, validation, or filtering of the external content before it is translated or incorporated into the SPEC product half.
Audit Metadata