scientific-slides
[EXPERIMENTAL] Build slide decks and presentations for research talks using Nano Banana Pro AI. Generates stunning PDF presentations with AI-generated slides. Use for conference presentations, seminar talks, thesis defense slides, or any scientific talk. Provides slide structure, design guidance, timing recommendations, and visual validation.
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 documents a --api-key CLI option (and shows exporting a key placeholder), which encourages passing API keys on the command line (requiring the key to be embedded verbatim) — an insecure exfiltration-prone pattern even though an env var alternative is mentioned.
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 only outsider-controlled text ingested at runtime is the user-supplied CLI `prompt` passed into `scripts/generate_slide_image.py` (and optional `--attach` image files), and there is no required workflow step that reads externally authored free text without an explicit item/prompt choice.
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's runtime scripts call the OpenRouter service to generate images (the AI inference is executed remotely) using the base API URL https://openrouter.ai/api/v1 and instruct users to obtain a key at https://openrouter.ai/keys, so the external OpenRouter endpoints are required at runtime.
- 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.