reader-knowledge
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides purely instructional content for narrative analysis and modeling reader knowledge. It contains no executable scripts, shell commands, or network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes user-provided narrative text. Ingestion point: Narrative content processed by the agent. Boundary markers: Absent. Capability inventory: Local file-write to
reader/READER_STATE.md. Sanitization: Absent. The risk is assessed as safe due to the lack of network access, command execution, or other exploitable capabilities.
Audit Metadata