graph-rag

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains only documentation and strategy guidance in markdown. No code, shell commands, or external dependencies are included.
  • [PROMPT_INJECTION]: The skill describes a process for reading external data sources, creating an indirect prompt injection surface. Evidence Chain: 1. Ingestion points: SKILL.md (Step 2) refers to entities, files, symbols, tables, and services. 2. Boundary markers: None specified for the prompt context assembly in SKILL.md. 3. Capability inventory: No executable tools or scripts are shipped with this skill. 4. Sanitization: No sanitization or validation of retrieved content is mentioned in the retrieval process.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 03:48 PM