systems-awareness-iceberg
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or dangerous commands were detected. The skill is a text-based prompt designed for classroom inquiry.
- [PROMPT_INJECTION]: The skill interpolates untrusted user input into its prompt template, creating a potential surface for indirect prompt injection. However, since the skill has no associated tools, scripts, or permissions to access the file system or network, the impact is negligible.
- Ingestion points:
focal_event,context,existing_evidence(SKILL.md) - Boundary markers: Absent
- Capability inventory: None detected
- Sanitization: Absent
Audit Metadata