media-probe-api
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches supplemental model documentation and parameter schemas from the vendor's website at
https://www.pixazo.ai/models/media-probe-api.mdduring execution to resolve field names and values. - [INDIRECT_PROMPT_INJECTION]: The skill incorporates external content into the agent's context, creating a surface for potential instruction overrides via remote data.
- Ingestion points: Remote Markdown documentation (
SKILL.md) and user-provided media URLs. - Boundary markers: Absent; there are no instructions to delimit or ignore potential commands within the fetched documentation.
- Capability inventory: Network requests (HTTP POST) to the API gateway at
gateway.pixazo.ai. - Sanitization: Absent; the skill does not define validation or filtering for the content retrieved from external URLs before processing.
Audit Metadata