linkedin-content

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the platform CLI and additional content creation modules using npx skills add from repositories associated with the platform vendor.
  • [COMMAND_EXECUTION]: The skill utilizes a specialized CLI (belt) to execute various platform-hosted applications for market research (tavily/search-assistant), image generation (falai/flux-dev-lora), and social media interaction (x/post-create).
  • [PROMPT_INJECTION]: The skill incorporates an indirect prompt injection surface by consuming data from external search results via the search assistant tool. Malicious instructions embedded in processed web content could potentially influence the agent's output formatting or content strategy.
  • Ingestion points: Data enters the context from the tavily/search-assistant app output.
  • Boundary markers: None identified in the provided instructions to separate external data from system instructions.
  • Capability inventory: The skill has the capability to generate images and post content to X (Twitter) using the belt CLI.
  • Sanitization: There are no explicit instructions for sanitizing or validating the search results before they are used for content generation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 07:15 PM
Security Audit — agent-trust-hub — linkedin-content