etsy-tony-full-gigab2b-photos
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external GigaB2B product URLs, SKU records, and API responses to generate content.
- Ingestion points: Sections 1 and 2 of
SKILL.mddescribe reading product titles, Item Codes, URLs, and image references from external pages and API records. - Boundary markers: The instructions do not define clear delimiters or secondary validation steps to isolate potentially malicious instructions embedded in the external product data.
- Capability inventory: The skill has the ability to navigate the browser, write files (e.g.,
manifest.json,product-title.txt), and invoke image generation tools. - Sanitization: There are no explicit sanitization or filtering steps mentioned for the content retrieved from external sources.
- [METADATA_POISONING]: The
SKILL.mdfile contains instructions to redirect users to an external Douyin (TikTok China) account (93440780745) for "Skills" support and tutorials. While this appears to be a vendor-owned resource for support, it encourages off-platform interaction through instructions embedded in the skill documentation.
Audit Metadata