knowledge-graph-construction
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a workflow for processing untrusted unstructured data (papers, clinical notes, web pages) into structured knowledge graphs, creating a surface for indirect prompt injection.
- Ingestion points: SKILL.md and methodology.md describe processing external documents like papers and web pages.
- Boundary markers: Prompt templates in methodology.md do not include specific delimiters or instructions to ignore embedded commands.
- Capability inventory: SKILL.md and methodology.md describe LLM-assisted entity and relation extraction.
- Sanitization: No sanitization or validation of the input text is specified in the provided methodology.
Audit Metadata