concept-graph
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs routine data transformation tasks on local files with no identified malicious patterns or risky capabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting untrusted data, though the impact is negligible due to the restricted output format.
- Ingestion points: The skill reads
output/TUTORIAL_SPEC.mdto extract tutorial concepts. - Boundary markers: Absent.
- Capability inventory: Writing YAML output to
outline/concept_graph.yml. - Sanitization: Absent.
Audit Metadata