ai-social-media-content

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 instructs the agent/user to execute a remote script using curl -fsSL https://cli.inference.sh | sh. This 'pipe to shell' pattern from a non-trusted domain is a major security risk that grants the remote server full control over the local execution environment.
  • [EXTERNAL_DOWNLOADS] (HIGH): The skill downloads and installs additional components from the untrusted inference-sh organization via npx skills add, which facilitates the execution of unverified remote code.
  • [COMMAND_EXECUTION] (MEDIUM): Broad shell execution permissions are defined for the infsh utility (Bash(infsh *)), permitting the agent to perform any subcommand including those handling authentication and remote process spawning.
  • [PROMPT_INJECTION] (LOW): The skill demonstrates a vulnerability to indirect command injection where user-controlled variables (like $topic) are interpolated directly into shell strings without sanitization or boundary markers.
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, 01:36 AM
Security Audit — agent-trust-hub — ai-social-media-content