finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the external environment which could contain malicious instructions designed to manipulate the agent's logic during the integration process.
- Ingestion points: The skill reads and reports output from project test suites (Step 1) and various git commands (Step 2, 5, 6).
- Boundary markers: Absent. The instructions do not specify using delimiters or 'ignore' instructions for the ingested output.
- Capability inventory: The skill has the capability to execute shell commands including
git,npm,cargo,pytest,go, andcd. - Sanitization: Absent. There is no mention of escaping or validating the command outputs before they are processed by the agent.
Audit Metadata