literature-review
Answer literature-review requests with a concise, source-grounded narrative by default. Escalate to PRISMA screening, evidence tables, figures, files, or PDFs only when the user explicitly asks for a systematic, scoping, or publication-formatted review.
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
In “literature-review”, the agent’s required systematic-review workflow ingests outsider-authored free text by reading titles/abstracts and potentially full texts obtained from public research databases (e.g., PubMed/bioRxiv/arXiv/Semantic Scholar) during phases 2–3 when screening/search results and documents are processed.
- 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.