growth-loops
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data provided through the
$ARGUMENTSvariable, creating a surface for potential instruction injection. - Ingestion points: Data enters the skill context via
$ARGUMENTSinSKILL.md(Product description, user demographics, etc.). - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the input data.
- Capability inventory: The skill performs text analysis and generation only; it lacks any subprocess execution, file system writes, or network operations.
- Sanitization: There is no evidence of input validation or sanitization for the provided arguments.
Audit Metadata