apply-all-findings
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes code review findings from external sources to generate checklists and automate the creation of GitHub issues.
- Ingestion points: Findings list gathered from external artifacts in Step 1 (e.g., from
comprehensive-review). - Boundary markers: Uses markdown list structures and code blocks to delimit findings.
- Capability inventory: Execution of GitHub CLI (
gh) for issue management and Node tools (pnpm) for local verification. - Sanitization: No explicit content sanitization or validation is specified before interpolating finding text into command arguments.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage GitHub project metadata and verify code changes.
- Evidence: Use of
gh issue create,gh label create,gh issue edit,pnpm lint,pnpm test,pnpm typecheck, andpnpm build. These commands are standard operations for the skill's stated purpose of implementing and tracking code improvements.
Audit Metadata