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 Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a data lineage tracker using standard Python classes. The logic is self-contained and does not perform any external network requests or unauthorized file system access.
- [SAFE]: No obfuscation or hidden instructions were detected. The Python code is clear and its behavior matches the stated purpose of managing data audit trails.
- [SAFE]: The skill uses standard libraries such as
dataclasses,hashlib, anduuidfor data integrity and identification, which is appropriate for its described function. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data, creating a potential attack surface. 1. Ingestion points: User-supplied CSV, Excel, and JSON data. 2. Boundary markers: Absent. 3. Capability inventory: No dangerous capabilities such as shell execution or network access are implemented in the skill logic. 4. Sanitization: Not explicitly implemented in the provided code logic. Severity is SAFE due to the lack of exploitable capabilities.
Audit Metadata