land-pr
Land lossless-claw pull requests safely; use when asked whether a PR is ready, whether CI passes, to merge or land a PR, or to perform maintainer closeout after review.
71
88%
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
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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
This workflow reads PR/issue metadata (including outsider-authored PR title/body-related fields, author, and candidate issue comments/bodies) via `gh pr view`, `gh pr checks`, and `gh issue view` at runtime, and those returned values become text in the agent’s LLM context—an indirect prompt-injection pathway from outsider content.
- Repository
- Martian-Engineering/lossless-claw
- Commit
db67593
- 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.