issue-decomposition
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from existing GitHub issues (titles, descriptions, and acceptance criteria) to generate new sub-tasks and memory entries.
- Ingestion points: Step 1 involves reading the parent issue thoroughly from GitHub.
- Boundary markers: No specific boundary markers or instructions to ignore instructions within the parent issue are present.
- Capability inventory: The skill can execute GitHub CLI commands (
gh issue create,gh issue edit) and update internal memory structures. - Sanitization: No explicit sanitization or escaping of input from the parent issue is described before interpolation into new issue bodies or memory updates.
- [COMMAND_EXECUTION]: The skill instructions include shell commands for the GitHub CLI to automate project management tasks.
- Evidence: Specifically uses
gh issue create,gh issue edit, andgh project item-addin steps 3, 4, and 6 to modify repository state.
Audit Metadata