gitflow-feature-workflow
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes Git operations for branch management and lifecycle, including destructive commands like branch deletion. It also executes project-specific verification tools (testing, linting) as defined in the repository's configuration files.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting untrusted data from the local repository environment.
- Ingestion points: Project context is loaded from
AGENTS.md,README.md,CHANGELOG.md, and Git status/log output. - Boundary markers: No specific delimiters or safety instructions are used to isolate content read from these files from the agent's instructional context.
- Capability inventory: The agent has permissions to perform Git commits, merges, and pushes, and to execute shell commands specified in the repository's documentation.
- Sanitization: The skill includes instructions for the agent to manually inspect diffs for secrets, but lacks automated sanitization for instructions embedded in the documentation it reads.
Audit Metadata