session-logger
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (LOW): The skill creates a vulnerability surface for Indirect Prompt Injection (Category 8) by extracting content from untrusted conversations into logs used for agent learning. Evidence: 1. Ingestion points: Processes current conversation history. 2. Boundary markers: Absent in the logging templates. 3. Capability inventory: Uses Read, Write, Edit, and Bash tools for file and directory management. 4. Sanitization: None performed on extracted user content before persistence to the filesystem.
Audit Metadata