image-gen
Generate images via Nano Banana (Gemini 2.5/3.1 Flash Image) on OpenRouter. Use when the user asks to draw, illustrate, render or generate any kind of picture/diagram/scene.
68
83%
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 skill’s required workflow sends the user-provided `prompt` in `SKILL.md:25-33` as chat message text to OpenRouter and then ingests the model’s returned free-text `message.content` back into agent context via the returned `text_note` (`SKILL.md:50-51`), so outsider-authored text (the third-party model response) is fed into the LLM context.
- Repository
- EverMind-AI/Raven
- Commit
4c2eb70
- 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.