pr-writer
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local
gitandgh(GitHub CLI) commands to inspect the repository state and perform pull request operations. These are standard tools used according to their intended purpose. - [EXTERNAL_DOWNLOADS]: It references official engineering documentation from
develop.sentry.dev. These links point to a well-known service and do not execute remote code. - [PROMPT_INJECTION]: There is a surface for indirect prompt injection as the agent reads output from
git logandgit diffto construct pull request descriptions. Maliciously crafted commit messages or code changes could potentially influence the agent's output. - Ingestion points: Output from
git logandgit diffinSKILL.md. - Boundary markers: Uses a defined Markdown structure for the description but lacks explicit instructions to ignore prompts within the ingested data.
- Capability inventory: Can create and modify pull requests via
gh pr createandgh apiinSKILL.md. - Sanitization: No sanitization is performed on the ingested git data before processing.
Audit Metadata