auto-context-mapper

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMDATA_EXFILTRATION
Full Analysis
  • Data Exposure & Access (MEDIUM): The skill is explicitly designed to identify and aggregate data across sensitive tiers, including 'Confidential' and 'Personal' storage. It mentions pulling budget-variance reports and technical debt logs into the agent's active context. While this is the primary purpose, it presents a high risk of sensitive data exposure if the agent is queried with malicious intent.
  • Indirect Prompt Injection (LOW): The skill has a large attack surface as it processes untrusted file content from the project directory. Ingestion points: Files located in the directory provided via the 'dir' argument. Boundary markers: None specified in the documentation or configuration. Capability inventory: Automatic file discovery and reading across security tiers. Sanitization: No sanitization or safety-filtering logic is described for the content being read before it is used to resolve context queries.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:49 PM