Skills
skills/inference-sh-9/skills/press-release-writing/Gen Agent Trust Hub

press-release-writing

Fail

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructs the user to execute an installation script directly from an external URL by piping the output of a network request to the shell.
  • Evidence: curl -fsSL https://cli.inference.sh | sh in SKILL.md.
  • Source: https://cli.inference.sh (matches author/vendor context).
  • [COMMAND_EXECUTION]: The skill uses the vendor's CLI tool to execute various applications and login to their service.
  • Evidence: infsh login, infsh app run tavily/search-assistant, infsh app run exa/search, and infsh app run exa/answer.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data retrieved from external web searches.
  • Ingestion points: External content fetched via tavily/search-assistant and exa/search (SKILL.md).
  • Boundary markers: No delimiters or instructions to ignore embedded commands are present in the provided templates.
  • Capability inventory: The skill has permission to execute shell commands via the Bash(infsh *) tool.
  • Sanitization: No evidence of sanitization or validation of the fetched external data.
  • [EXTERNAL_DOWNLOADS]: The skill downloads and adds external dependencies using a package manager.
  • Evidence: npx skills add inference-sh/skills@web-search and npx skills add inference-sh/skills@prompt-engineering.
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