settle-effort
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh) to perform repository management actions, such as listing pull requests, merging branches, editing pull request metadata, and creating labels or issues. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from pull request descriptions and handoff documents to determine which follow-up actions to run and which work to carry over.
- Ingestion points: Pull request descriptions and handoff files (referenced in SKILL.md, Step 3).
- Boundary markers: None specified to isolate or identify data versus instructions within the ingested content.
- Capability inventory: GitHub CLI commands (
gh pr merge,gh issue create,gh label create,gh pr edit) and arbitrary command execution for follow-up tasks defined in the delivery documents (SKILL.md, Steps 2, 4, and 5). - Sanitization: No evidence of sanitization or validation of the follow-up instructions found in the pull request context before execution.
Audit Metadata