ai-marketing-videos
Fail
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The Quick Start section includes the command 'curl -fsSL https://cli.inference.sh | sh', which downloads and executes a remote script without verification. This 'pipe-to-shell' pattern is a high-risk practice that can lead to arbitrary code execution if the remote source or connection is compromised.
- [EXTERNAL_DOWNLOADS]: The skill requires downloading and running external software from 'https://cli.inference.sh', a domain outside the primary scope of the skill's author.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8). It ingests untrusted user prompts and interpolates them into JSON payloads for 'infsh' tool calls without sanitization or protective boundary markers. * Ingestion points: User-provided prompts in 'infsh app run' examples (SKILL.md). * Boundary markers: Absent. * Capability inventory: Subprocess execution of 'infsh' apps via Bash. * Sanitization: Absent.
Recommendations
- HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata