systems-awareness-iceberg
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and a text-based prompt instructions. No malicious code, obfuscation, or persistence mechanisms were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided data (focal event, context, evidence) which is interpolated into the final prompt. While it lacks explicit boundary markers for these inputs, the skill does not have access to sensitive tools, file system operations, or network capabilities, which prevents any functional exploitation via this vector.
Audit Metadata