mermaid
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input directly through the
$ARGUMENTSvariable, which provides an attack surface for malicious instructions targeting the agent. - Ingestion points: User requirements are processed via the
$ARGUMENTSplaceholder at the end ofSKILL.md. - Boundary markers: No delimiters or explicit instructions to ignore potentially harmful commands are present around the user-provided input.
- Capability inventory: The skill is configured with access to
Read,Write, andEdittools. - Sanitization: The input is interpolated directly without any sanitization, validation, or escaping.
Audit Metadata