scientific-schematics
Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill includes examples that embed API keys as literal strings (api_key="your_openrouter_key" and a --api-key CLI flag), which would require an LLM to place secret values verbatim into generated code/commands and thus creates an exfiltration risk.
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
High-likelihood indirect prompt-injection via outsider free text: the agent takes the runtime diagram description (`prompt`) provided to `scripts/generate_schematic.py` (free-form user text, not validated here) and embeds it verbatim into LLM messages/prompts in `scripts/generate_schematic_ai.py` (e.g., `USER REQUEST: {user_prompt}` and `ORIGINAL REQUEST: {original_prompt}`), which Gemini 3 Pro then reads during quality review.
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 skill makes runtime API calls to OpenRouter (base URL "https://openrouter.ai/api/v1") and directly uses the model's review/critique text to construct improved prompts (see improve_prompt/current_prompt), so external content from that URL controls prompt generation.
- Repository
- foryourhealth111-pixel/Vibe-Skills
- Commit
d5ae560
- 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.