background-removal
Fail
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- REMOTE_CODE_EXECUTION (HIGH): The skill documentation in SKILL.md contains a command to download and execute a remote script using
curl -fsSL https://cli.inference.sh | sh. This pattern is a primary vector for remote code execution from an untrusted third-party source. - EXTERNAL_DOWNLOADS (MEDIUM): The skill references and installs external components using
npx skills add inference-sh/skills, which involves downloading and executing code from non-standard, unverified sources. - COMMAND_EXECUTION (LOW): The skill requires the Bash tool with
infsh *permissions in SKILL.md to interact with the Inference platform, which could be exploited if the CLI tool or the platform is compromised. - PROMPT_INJECTION (LOW): Detected an Indirect Prompt Injection surface. 1. Ingestion points:
image_urlandpromptparameters in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Bash command execution via theinfshCLI (SKILL.md). 4. 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