context-graph
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references multiple documentation files and conceptual diagrams hosted on the author's GitHub repository (jacob-balslev/skill-graph). These resources provide grounding and technical context for the multi-graph model.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a framework for analyzing workspace artifacts such as markdown files, frontmatter, and command registries. This ingestion of potentially untrusted local data is a standard operation for workspace auditing and is mitigated by the skill's focus on deterministic synthesis signals rather than runtime LLM inference for graph generation.
Audit Metadata