open-pr
Open a pull request on the Kiln repo with a semantic-commit title and a structured description (one-line TLDR, summary, implementation bullets, warnings, optional Mermaid diagram, collapsible examples and screenshots). Also covers the short watch window for review-bot comments and CI. Use when the user asks to open, create, or raise a PR, to write or rewrite a PR description, or to update a PR after a push.
73
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow instructs the agent to read GitHub pull request review comments and CI logs during the watch window, which are outsider-authored inputs capable of containing free-text prompt injections.
- Repository
- Kiln-AI/Kiln
- Commit
067f294
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.