Gen Agent Trust Hub

pr-writer · getsentry/skills

Passed

Provider summary

The skill is generally safe and designed to automate Sentry's pull request workflow using the GitHub CLI. It includes privacy-conscious instructions to avoid leaking sensitive data. A low-risk surface for indirect prompt injection exists, as the skill processes untrusted commit messages and existing PR descriptions which could be used to manipulate the agent's behavior or attempt command injection through shell heredoc escaping.

The provider classified the analyzed snapshot as NONE risk. This result applies to the content available at audit time.

Interpretation

Compare the repository, publisher, and installation command before continuing.

Review SKILL.md, scripts, and allowed tools. Artificial Atlas never executes them during indexing.

Use the narrowest possible scope and avoid broad credentials for third-party skills.