pr-write
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands like
git diffandgit diff --statto analyze changes before writing the PR body. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from git diffs and commit messages which may contain malicious instructions designed to influence the agent's output.
- Ingestion points: Git diff output and commit history referenced in the 'Workflow' section of
SKILL.md. - Boundary markers: The skill instructs the agent to use specific markdown headers (e.g.,
## What,## Why) for the generated output, which helps delineate the AI's response. - Capability inventory: Shell command execution via the
gitCLI. - Sanitization: No explicit content sanitization or instructions to disregard embedded commands within the diffed text are provided.
Audit Metadata