to-wireframe
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain malicious instructions designed to influence the agent's behavior during the wireframing process.\n
- Ingestion points: Untrusted text is ingested via the
briefparameter, and image data is ingested via theimageparameter as described inSKILL.md.\n - Boundary markers: The instructions do not specify explicit delimiters or 'ignore' instructions to separate the untrusted input content from the skill's core logic.\n
- Capability inventory: The skill performs file system write operations to an
outputpath or a path derived from the input file location (SKILL.md).\n - Sanitization: The skill includes a minor sanitization instruction to 'Use labels with basic letters and numbers to avoid invalid XML' for SVG output, but lacks broader sanitization for the input text itself.
Audit Metadata