clarify
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external UI content and code snippets, which presents a surface for indirect prompt injection attacks.
- Ingestion points: External data enters the skill's context through the
$ARGUMENTSvariable, intended to contain UI copy or source code. - Boundary markers: The skill instructions lack explicit delimiters or instructions for the agent to ignore potentially malicious commands embedded within the provided UI text.
- Capability inventory: The skill possesses the capability to modify the filesystem ("edit the code") based on the processed input.
- Sanitization: No evidence of sanitization, validation, or escaping logic is present to filter malicious instructions within the
$ARGUMENTScontent.
Audit Metadata