skills/sebas-aikon-intelligence/antigravity-awesome-skills/finishing-a-development-branch/Gen Agent Trust Hub
finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard development tools, including Git for branch management and project-specific test runners (npm, cargo, pytest, go). These commands are necessary for the skill's stated purpose of automating implementation completion.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as test results, branch names, and code implementation details to generate reports and Pull Request content.
- Ingestion points: Test suite output (bash), branch names (git), and implementation summaries (provided by the agent/user).
- Boundary markers: The skill utilizes shell heredocs (
EOF) to delimit multi-line PR bodies, which helps prevent content from being interpreted as shell commands within that specific context. - Capability inventory: The skill has the capability to execute shell commands (
bash) and interact with remote repositories (git push,gh pr create). - Sanitization: While it uses heredocs for the PR body, there is no explicit sanitization for PR titles or branch names interpolated into shell commands. However, the risk is mitigated by the standard operational context of a development environment.
Audit Metadata