skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
67
81%
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.
2 low severity findings. 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
The required workflow uses `eval-viewer/generate_review.py` to read and embed arbitrary text/markdown from runtime-produced run files like `outputs/transcript.md` / `user_notes.md` / `grading.json` into the served HTML (and thus into the context shown to the reviewing model/user), where those files can contain outsider-authored free text from the executed eval prompts and user feedback.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The eval viewer HTML (eval-viewer/viewer.html) includes a runtime-loaded remote JavaScript library (https://cdn.sheetjs.com/xlsx-0.20.3/package/dist/xlsx.full.min.js) which will be fetched and executed in the user's browser when the viewer is opened, representing a runtime external dependency that executes remote code.
- Repository
- UnicomAI/wanwu
- Commit
f618458
- 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.