each-sense
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill's request schema provides a parameter named 'enable_safety_checker' which can be set to 'false' to intentionally bypass safety filters and allow the generation of restricted or NSFW content.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external sources, which presents an attack surface for indirect prompt injection.
- Ingestion points: Data enters the agent context through external URLs provided in the 'image_urls' parameter and through content retrieved by the 'web_search' tool.
- Capability inventory: The skill has the ability to execute generative models, build and trigger workflows, and perform web searches across its various tools and scripts.
- Boundary markers: The documentation does not indicate the presence of delimiters or instructions meant to isolate the agent from potentially malicious commands embedded in external images or search results.
- Sanitization: There is no evidence of content sanitization or validation performed on data retrieved from external sources before it is processed by the AI models.
Audit Metadata