knowledge-synthesis
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process results from external sources like chat, email, and cloud storage. This represents an indirect prompt injection surface where untrusted data enters the agent context. The instructions mitigate this by requiring strict source attribution and narrative synthesis rather than raw execution.
- [SAFE]: No malicious code, prompt injection overrides, or data exfiltration patterns were detected. The skill consists entirely of instructional markdown without any attached scripts or tool calls.
Audit Metadata