finalize
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository to perform its analysis phase.
- Ingestion points: The output of
git diff --cachedandgit diff --cached --statis read to categorize changes (e.g., refactoring, bug fix) and decide on splitting units inSKILL.md. - Boundary markers: No specific delimiters or "ignore instructions" wrappers are mentioned when processing the diff content.
- Capability inventory: The skill can execute other skills (
/polish-code,/ship,/split-and-ship), manage tasks viaTaskCreate, and perform git operations. - Sanitization: There is no explicit sanitization or validation of the content provided by the diff output before it is used to influence the workflow logic.
- [COMMAND_EXECUTION]: The skill invokes standard system commands to inspect the state of the repository.
- Evidence: Uses
git diff --cached --statandgit diff --cachedto understand the scope of changes during the "Ship It" phase.
Audit Metadata