literature_to_hypothesis
Extracts falsifiable scientific hypotheses (if-then form) from multiple PubMed articles, abstracts, or full texts. Synthesizes supporting evidence, contradictions, and experimental validation suggestions into a structured Markdown report for hypothesis-driven research planning.
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 skill’s runtime ingestion step explicitly fetches and extracts text from outsider-authored scientific literature (PubMed abstracts and optionally full texts) provided via PMIDs/DOIs or PDF paths, which the LLM then reads for hypothesis extraction.
- Repository
- wu-yc/LabClaw
- Commit
df37802
- 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.