scientific-slides

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt documents an --api-key CLI option and shows setting OPENROUTER_API_KEY in-shell (including an explicit example), which enables and encourages embedding API keys in commands/outputs (an insecure pattern that can expose secrets verbatim).

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md and REFERENCE.md explicitly require using the "research-lookup" flow to fetch public papers and instruct attaching/including user-provided or working-directory figures (and including citations) so the agent ingests open/public third-party content that will be interpreted and used to drive slide-generation prompts and actions.