when-to-become-studio
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided information such as a founder's name and assessment responses to generate a localized report. While it interpolates this data into a markdown file, the impact is confined to a local file-write operation.
- Ingestion points: User input for the
{founder-name}variable and the assessment signals inSKILL.md. - Boundary markers: The skill does not use explicit delimiters to isolate user-provided data from instructions in the generated output.
- Capability inventory: Performs file-write operations to the
./portfolio/directory. - Sanitization: There is no explicit sanitization logic described for the
{founder-name}variable, which is used to construct a local file path.
Audit Metadata