wait-what
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a text-based instruction set that directs the agent to re-pitch content using ASD-STE100 Simplified Technical English. No malicious patterns, command execution, or exfiltration attempts were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to use ubiquitous language from
CONTEXT.md. This creates an attack surface where malicious instructions could be embedded in the referenced file to influence agent behavior. - Ingestion points:
CONTEXT.mdreference inSKILL.md. - Boundary markers: None provided.
- Capability inventory: None; tool invocation is explicitly disabled (
disable-model-invocation: true). - Sanitization: None provided.
Audit Metadata