Skills
▥
skills/inference-sh-9/skills/competitor-teardown/Gen Agent Trust Hub

competitor-teardown

Fail

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches a CLI installation script from the vendor's domain at https://cli.inference.sh.
  • [REMOTE_CODE_EXECUTION]: Executes the downloaded installation script directly by piping the web response to the shell (| sh).
  • [COMMAND_EXECUTION]: Uses the infsh command-line interface via Bash(infsh *) to execute various tasks like search, extraction, and browser automation.
  • [REMOTE_CODE_EXECUTION]: Utilizes an internal Python executor (infsh/python-executor) to dynamically generate data visualizations using matplotlib.
  • [PROMPT_INJECTION]: Subject to potential indirect prompt injection due to processing unverified content from the open web.
  • Ingestion points: Reads data from external sources using tavily/search-assistant, exa/search, and tavily/extract (SKILL.md).
  • Boundary markers: No specific delimiters or safety instructions are used to separate external data from the analysis framework.
  • Capability inventory: The skill has access to Bash and a Python execution environment.
  • Sanitization: No evidence of sanitization or filtering of external website content before processing.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 25, 2026, 05:35 PM