scientific-schematics
[EXPERIMENTAL] 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 contains explicit examples that place API keys directly in code/CLI (api_key="your_openrouter_key" and --api-key "sk-or-v1-..."), which instructs the agent to include secret values verbatim in generated outputs/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
In `scripts/generate_schematic.py` → `scripts/generate_schematic_ai.py` (`generate_iterative()`), the user-supplied `prompt` is embedded into LLM review/generation messages (`review_prompt` and `current_prompt`) and therefore the runtime ingests free text directly authored by the caller.
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 uses the returned review critique from the remote Gemini model to modify subsequent generation prompts (review → improve_prompt), so external content fetched at runtime directly controls the agent's prompts.
- Repository
- synthetic-sciences/openscience
- Commit
a820c2f
- 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.