finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it is designed to analyze existing codebases and repository evidence.
- Ingestion points: The skill inspects repository files, current versions, and user inputs as part of its initialization workflow (SKILL.md).
- Boundary markers: The instructions do not explicitly define delimiters or specific "ignore embedded instructions" warnings for the content read from the repository.
- Capability inventory: The skill has the capability to execute tools via
sandbase_runand perform file system analysis. - Sanitization: There are no explicit instructions for sanitizing or escaping content retrieved from external files before processing.
- Mitigation: The risk is addressed by quality gates requiring the agent to verify real outputs with tests, obtain user confirmation for all paid external calls, and refrain from committing or pushing changes without explicit user request.
Audit Metadata