finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface where untrusted or generated data is ingested into the agent context.
- Ingestion points: The skill ingests a summary and test plan, which are then interpolated into a
gh pr createshell command in Step 4. - Boundary markers: No specific delimiters or instructions are used to separate the generated PR content from the command instructions.
- Capability inventory: The skill possesses the capability to perform destructive Git operations (branch deletion) and network-facing operations (pushing to origin, creating PRs via
gh). - Sanitization: The skill lacks explicit sanitization or validation of the PR body content before execution in the shell.
Audit Metadata