background-removal
Fail
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- Unverifiable Dependencies & Remote Code Execution (HIGH): The skill instructs the agent/user to run
curl -fsSL https://cli.inference.sh | sh. This is a dangerous execution pattern that runs an unverified remote script from a non-whitelisted source. - Unverifiable Dependencies & Remote Code Execution (HIGH): The documentation recommends
npx skills add inference-sh/skills, which executes code from an untrusted third-party npm organization. - Command Execution (MEDIUM): The skill requests permission to execute
Bash(infsh *). This capability depends on the security of the third-partyinfshbinary installed via the insecure shell pipe. - Indirect Prompt Injection (LOW): The skill is susceptible to indirect injection through user-controlled image URLs. 1. Ingestion points:
image_urlparameters in JSON inputs. 2. Boundary markers: Absent. 3. Capability inventory: Bash execution viainfsh. 4. Sanitization: None detected.
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