web-asset-generation
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied metadata into generated files without sanitization.
- Ingestion points: The
AssetConfiginterface inSKILL.mddefines fields likesiteName,siteUrl, anddescriptionwhich are populated from user or brand specifications. - Boundary markers: No delimiters or explicit instructions are provided to the agent to treat these inputs as data rather than instructions.
- Capability inventory: The skill uses the
fsmodule for filesystem operations (mkdirSync,writeFileSync) and thesharplibrary to read from the localsourcepath and write generated images to theoutputDir. - Sanitization: The implementation in
SKILL.mddirectly interpolates input strings into an SVG template (generateOgImage) and HTML meta tags (generateHtmlTags) without escaping or validation, potentially allowing malicious content to be embedded in the output web assets.
Audit Metadata