topaz-upscale-video
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructional examples for interacting with the EachLabs API for video processing. It follows security best practices by using environment variables for authentication and structured JSON for data transmission.
- [DATA_EXPOSURE]: Sensitive credentials are not hardcoded; instead, the skill correctly references an environment variable
$EACHLABS_API_KEYfor API access. - [INDIRECT_PROMPT_INJECTION]: The skill includes an ingestion surface where external content is processed via the
video_urlparameter. - Ingestion points: The
video_urlparameter in thecurlcommands (SKILL.md). - Boundary markers: The skill uses structured JSON payloads which act as data boundaries.
- Capability inventory: Uses
Bash(curl *)to send data to a remote API. - Sanitization: None specified in the client-side instructions, as processing occurs on the remote server.
Audit Metadata