linkedin-content

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches installation instructions from the author's official GitHub repository (inference-sh/skills).
  • [COMMAND_EXECUTION]: Uses the infsh CLI and npx to manage skills and execute platform-specific applications for content research and image generation.
  • [PROMPT_INJECTION]: The skill incorporates external tool outputs from a search assistant, which introduces a surface for indirect prompt injection. Ingestion points: untrusted data from search results via infsh app run tavily/search-assistant in SKILL.md. Boundary markers: absent. Capability inventory: includes subprocess execution via infsh and npx. Sanitization: absent.
  • [SAFE]: No obfuscation, hardcoded credentials, or persistence mechanisms were found. The skill's operations are transparent and restricted to the vendor's ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 09:05 PM