data-lineage-guardian
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- Prompt Injection (LOW): High vulnerability to Indirect Prompt Injection (Category 8). The skill is designed to ingest and process data from external, potentially attacker-controlled sources.
- Ingestion points: Processes data from project directories, production databases, and APIs.
- Boundary markers: The documentation lacks any mention of delimiters or instructions to ignore embedded commands in the data being mapped.
- Capability inventory: Accesses 'main DB' and 'frontend components' with the ability to write findings to a user-specified output file path.
- Sanitization: No sanitization or validation of the ingested data is described before it is analyzed by the agent.
- Data Exposure & Exfiltration (LOW): The skill has a high-privilege data access surface (Category 2). It is explicitly designed to identify and monitor PII and 'prioritize the most specific secrets.' While this is the intended purpose for data lineage and GDPR compliance, it represents a path for potential data exposure if the agent's logic is subverted.
Audit Metadata