ai-product-photography

Fail

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • REMOTE_CODE_EXECUTION (HIGH): The skill contains the command curl -fsSL https://cli.inference.sh | sh. This is a classic 'pipe-to-shell' vulnerability where an external script is executed immediately upon download. The source inference.sh is not a recognized trusted repository or organization.
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill relies on an external binary downloaded from dist.inference.sh. Although the documentation claims SHA-256 verification, the installation logic itself is untrusted and could be modified at the source.
  • PROMPT_INJECTION (LOW): The skill is vulnerable to indirect prompt injection because it interpolates user-provided text directly into JSON payloads for shell commands.
  • Ingestion points: User-provided prompts in SKILL.md example commands.
  • Boundary markers: Absent; uses simple single/double quote wrapping which can be escaped.
  • Capability inventory: Capability to execute shell commands via Bash(infsh *) and interact with external APIs.
  • Sanitization: None detected; user input is passed directly to the infsh tool.
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
HIGH
Analyzed
Feb 19, 2026, 08:07 PM