resemble-detect
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain hidden instructions intended to influence the agent's behavior.
- Ingestion points: The skill accepts media URLs for audio, video, and images, as well as raw text content for detection and intelligence analysis via the Resemble AI API.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its own logic and the potentially adversarial content within analyzed media transcriptions or scene descriptions.
- Capability inventory: The skill makes network requests to
app.resemble.ai. It does not have permissions for local file system access, shell command execution, or dynamic code evaluation. - Sanitization: The skill does not implement sanitization or validation of the ingested external content to filter for potential injection patterns.
Audit Metadata