skills/pixazo-ai/skills/sync-lipsync/Gen Agent Trust Hub

sync-lipsync

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions prompt the agent to fetch additional model reference and polling logic from the official Pixazo documentation at pixazo.ai. It also references a package installation command for related skills via npx.
  • [COMMAND_EXECUTION]: Provides Bash, Python, and Node.js code samples for the agent to execute curl and HTTP requests to the gateway.pixazo.ai endpoint for video generation tasks.
  • [INDIRECT_PROMPT_INJECTION]: The agent is instructed to read external content from pixazo.ai to determine runtime API schemas, representing a potential ingestion point for external data.
  • Ingestion points: SKILL.md (instructions to fetch https://www.pixazo.ai/models/sync-lipsync.md)
  • Boundary markers: Absent
  • Capability inventory: Shell execution (curl), file write access (~/.pixazo/api-key), network operations via HTTP POST/GET
  • Sanitization: Absent
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 09:02 PM