resemble-detect
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill interacts exclusively with the official Resemble AI domain (app.resemble.ai) for all media analysis and detection tasks. It follows secure practices by using Bearer token authentication and explicitly instructing the agent to reject local file paths in favor of secure HTTPS URLs.
- [PROMPT_INJECTION]: The skill involves an indirect prompt injection surface as it ingests untrusted media from external URLs and allows natural-language queries to be performed on the output. This is a common characteristic of media analysis tools.
- Ingestion points: External media URLs and intelligence analysis responses (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: API calls to Resemble AI for detection and intelligence (SKILL.md).
- Sanitization: No specific sanitization or filtering of external content is defined.
Audit Metadata