Skills
skills/inference-sh-8/skills/content-repurposing/Gen Agent Trust Hub

content-repurposing

Fail

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The documentation provides a command to install the necessary CLI tool by piping a remote script from https://cli.inference.sh to the shell.- [EXTERNAL_DOWNLOADS]: The setup script downloads architecture-specific binaries and performs checksum verification from https://dist.inference.sh.- [COMMAND_EXECUTION]: The skill uses the infsh tool via Bash to execute specific application workflows for media generation.- [PROMPT_INJECTION]: The skill processes untrusted input data, such as blog posts and transcripts, to generate social media content, which presents a surface for indirect prompt injection.\n
  • Ingestion points: Data provided to infsh app run commands.\n
  • Boundary markers: Not present in the provided command examples.\n
  • Capability inventory: Shell command execution through the infsh CLI.\n
  • Sanitization: No sanitization of the input data is documented.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 27, 2026, 02:29 PM