quote-post
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied captions and image descriptions. This data ingestion creates a surface for indirect prompt injection; however, the skill has no dangerous capabilities such as network access, file system modifications, or shell execution that could be exploited. The instructions primarily drive text generation for manual copy-pasting by the user.\n- [PROMPT_INJECTION]: The instruction labeled as 'CRITICAL' at the beginning of the file is used to define the user experience and workflow start point. It does not target safety filter bypass or system prompt extraction.
Audit Metadata