data-lineage-tracer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted database artifacts and metadata which could contain malicious instructions.
- Ingestion points: Reads .sql files, schema definitions, ORM code, and database metadata (pg_views, information_schema.triggers) from the local project context and live database connections.
- Boundary markers: Absent; there are no specific instructions or delimiters provided to the agent to disregard instructions potentially embedded within the analyzed source code or database metadata.
- Capability inventory: The skill has the capability to write technical reports to the local filesystem in markdown and JSON formats.
- Sanitization: Absent; no validation or escaping of external content is performed before processing or including it in the output reports.
Audit Metadata