ai-product-photography

Fail

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • REMOTE_CODE_EXECUTION (CRITICAL): The skill recommends installing its CLI tool using curl -fsSL https://cli.inference.sh | sh. This 'pipe to shell' pattern from an unverified domain is a confirmed remote code execution vector that grants the remote server full control over the local environment without verification.
  • EXTERNAL_DOWNLOADS (HIGH): The skill downloads and executes software from https://cli.inference.sh, which is not an authorized or trusted source according to the security policy.
  • COMMAND_EXECUTION (MEDIUM): The skill utilizes the Bash tool to run the infsh CLI and perform batch operations. The lack of restriction on these commands, combined with shell interpolation, creates a significant attack surface.
  • PROMPT_INJECTION (LOW): The skill is vulnerable to Indirect Prompt Injection. Evidence: (1) Ingestion points: User-defined product names and prompt descriptions. (2) Boundary markers: Absent in the command templates. (3) Capability inventory: Full Bash tool access for infsh commands. (4) Sanitization: None identified in the skill instructions.
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
Risk Level
CRITICAL
Analyzed
Feb 18, 2026, 01:37 AM
Security Audit — agent-trust-hub — ai-product-photography