challenge
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of markdown documentation and natural language instructions. It does not include any scripts, executables, or automated system commands.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a command
/em:challenge <plan>which ingests untrusted user data (the 'plan'). - Ingestion points: The
<plan>variable in the command structure. - Boundary markers: None explicitly defined in the provided file.
- Capability inventory: None. The skill does not have file-write, network, or subprocess execution capabilities.
- Sanitization: Not present. However, because the skill has no dangerous system capabilities, the surface for indirect prompt injection is purely informational and represents a negligible security risk.
Audit Metadata