ai-marketing-videos
Fail
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads a setup script from the vendor's official installation domain (cli.inference.sh).
- [REMOTE_CODE_EXECUTION]: The skill uses the pattern
curl | shto install the vendor's CLI tool from their official domain. This is the documented installation method for the service. - [COMMAND_EXECUTION]: The skill makes extensive use of the
infshCLI tool to run AI models for video and audio. This capability is restricted via the manifest'sallowed-toolsfield. - [PROMPT_INJECTION]: The skill processes untrusted user input by interpolating natural language prompts into CLI command arguments.
- Ingestion points: prompt fields within
infsh app runcommands (SKILL.md). - Boundary markers: None identified.
- Capability inventory: Execution of the
infshCLI tool to run various AI models. - Sanitization: None identified.
Recommendations
- HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
Audit Metadata