skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/data-lineage-tracker/Gen Agent Trust Hub
data-lineage-tracker
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external data files and incorporates their content into reports and Mermaid diagrams, creating an indirect prompt injection surface.
- Ingestion points: User-provided CSV, Excel, and JSON data files referenced in instructions.md.
- Boundary markers: None identified; no delimiters are used to separate data from instructions.
- Capability inventory: The skill has filesystem access permissions as defined in claw.json.
- Sanitization: There is no evidence of input validation or content filtering before data is reflected in output reports.
Audit Metadata