ai-marketing-videos
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
infshcommand-line tool to run AI applications and process media assets. It includes shell-scripting patterns such as loops and redirection to orchestrate multi-step video creation workflows.- [EXTERNAL_DOWNLOADS]: The documentation references installation instructions and media assets hosted on the vendor's official GitHub repository and cloud storage infrastructure.- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it ingests untrusted user input to form video generation prompts. 1. Ingestion points: prompt fields in theinfsh app runcommands within SKILL.md. 2. Boundary markers: Absent; inputs are interpolated into JSON command payloads. 3. Capability inventory: Uses theinfshCLI tool for remote processing and local file redirection. 4. Sanitization: Not explicitly present in the provided templates.
Audit Metadata