pre-push-checks
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to interact with the repository and testing tools.\n
- Evidence: Use of
git status,git rev-parse,git diff,pnpm exec vitest, andgh pr checksthroughoutSKILL.md.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads data from the local repository (diffs, status, PR checks) and uses it to drive subsequent actions, creating a surface for potential injection via malicious file names or commit messages.\n - Ingestion points: Commands such as
git status,git diff, andgh pr checksinSKILL.mdbring external data into the agent's context.\n - Boundary markers: The instructions do not define specific delimiters to isolate repository data from the agent's instructions.\n
- Capability inventory: The skill employs shell command execution capabilities via
git,pnpm, andghacross the instructions inSKILL.md.\n - Sanitization: There is no evidence of sanitization or filtering applied to the repository data before it is processed by the agent.
Audit Metadata