graph-rag
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow for ingesting and synthesizing information from untrusted external sources, such as source code repositories and text corpora.
- Ingestion points: External source code and text documents identified in the extraction phase.
- Boundary markers: The skill does not provide specific delimiters or instructions to ignore embedded prompts within the ingested data.
- Capability inventory: The skill enables hierarchical summarization and graph-based retrieval, which can be influenced by the content of the processed data.
- Sanitization: No explicit content validation or sanitization steps are documented.
- [NO_CODE]: The skill consists exclusively of markdown documentation and does not include any executable scripts, binaries, or automated configuration files.
Audit Metadata