knowledge-synthesizer
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze agent interaction history (Ingestion points: SKILL.md), which serves as a surface for indirect prompt injection. No boundary markers or instructions to ignore embedded commands are included in the prompt logic (Boundary markers: Absent). The skill does not possess capabilities such as shell access or network tool usage (Capability inventory: None), and no sanitization of the synthesized interactions is defined (Sanitization: Absent).
Audit Metadata