ai-product-photography

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • Remote Code Execution (CRITICAL): The skill contains the installation pattern curl -fsSL https://cli.inference.sh | sh, which executes a remote script with current user privileges. This is a severe security risk as the script source is unverified and from an untrusted domain.\n- External Downloads (HIGH): The skill references and executes code from cli.inference.sh, which is not included in the list of Trusted External Sources. This lacks the security guarantees required for safe operation.\n- Indirect Prompt Injection (HIGH): The skill is highly vulnerable to command injection through untrusted user-controlled prompts.\n
  • Ingestion points: User-provided strings for image generation prompts are interpolated into bash commands in multiple examples in SKILL.md.\n
  • Boundary markers: No boundary markers or delimiters are used to separate user data from the executable command structure.\n
  • Capability inventory: The frontmatter grants Bash(infsh *) tool permissions, giving the skill the ability to execute arbitrary sub-processes via the CLI tool.\n
  • Sanitization: There is no evidence of sanitization, JSON escaping, or shell metacharacter filtering for the input variables used in commands.
Recommendations
  • CRITICAL: Downloads and executes remote code from untrusted source(s): https://cli.inference.sh - DO NOT USE
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 16, 2026, 07:28 AM