melech-idea-to-canvas
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process arbitrary user-supplied content, such as Slack threads or rough notes, to generate structured documentation.
- Ingestion points: The skill accepts a wide range of potentially untrusted data via the
@<input>reference inSKILL.md. - Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the ingested data.
- Capability inventory: The skill creates
.canvas.tsxfiles but does not have access to sensitive files, environment variables, or network operations. - Sanitization: The instructions do not specify sanitization or escaping protocols for the input text prior to artifact generation.
- [DYNAMIC_EXECUTION]: The skill generates executable code files based on the interpreted user input.
- Evidence: The skill is explicitly directed to "Create an actual .canvas.tsx artifact" based on the provided input, which involves script generation from templates.
Audit Metadata