understand-knowledge
Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.
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
Yes: the required workflow reads outsider-authored wiki markdown files from the user-supplied target directory (e.g., `wiki_root.rglob("*.md")` in `parse-knowledge-base.py`), places their free text into `scan-manifest.json` as `knowledgeMeta.content`, and then the Phase 3 `article-analyzer` subagents feed that content into the LLM context as “untrusted article data”.
- Repository
- Lum1104/Understand-Anything
- Commit
fe8c5bc
- 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.