skills/unifapi-agent/skills/threads/Gen Agent Trust Hub

threads

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation references external resources at https://mcp.unifapi.com for MCP server connectivity and https://unifapi.com for documentation and installation. These are official vendor resources belonging to the skill author.
  • [COMMAND_EXECUTION]: The README provides installation instructions using npx skills add unifapi-agent/agents, which involves command-line execution of a package. This is a standard installation method for the platform and targets the author's own namespace.
  • [PROMPT_INJECTION]: The skill processes untrusted public data from the Threads platform, which presents an indirect prompt injection surface.
  • Ingestion points: External data is ingested via threads/search and threads/users endpoints as specified in SKILL.md.
  • Boundary markers: Not explicitly defined in the instruction templates.
  • Capability inventory: The skill is limited to read-only operations and has no file-system write, command execution, or network-posting capabilities.
  • Sanitization: No specific sanitization or filtering of the ingested social media content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 10:29 AM
Security Audit — agent-trust-hub — threads