image-to-code
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to generate output reports and update indices/logs within a
llmwikidirectory after completing design tasks. This creates a surface where the agent processes potentially untrusted user prompts and writes derived content into persistent project files. - Ingestion points: User-provided design prompts and project descriptions processed in the implementation phase.
- Boundary markers: The instructions do not specify any delimiters or safety markers to isolate external data from the reporting logic.
- Capability inventory: The skill instructs the agent to perform file-write operations to
llmwiki/wiki/draft/uiux/,llmwiki/wiki/index.md, andllmwiki/wiki/log.md. - Sanitization: There are no explicit instructions for sanitizing, validating, or escaping the generated content before it is appended to the wiki files.
Audit Metadata