finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates untrusted data from the git environment into its execution flow.
- Ingestion points: The skill reads branch names and commit messages from the local environment in
SKILL.md(Steps 2, 4, and 5). - Boundary markers: There are no explicit delimiters or instructions to the agent to ignore potentially malicious content within branch names or commit bodies.
- Capability inventory: The skill has the capability to execute shell commands (
git,npm,gh) as shown inSKILL.md. - Sanitization: There is no evidence of sanitization or validation of the git metadata before it is interpolated into shell commands.
- [COMMAND_EXECUTION]: The skill uses various shell commands to perform development tasks, which is the primary and expected behavior of the tool.
- Evidence: The skill explicitly defines the use of
npm test,cargo test,git merge,git push, and the GitHub CLI (gh) for creating pull requests withinSKILL.md.
Audit Metadata