x-thread-crafter

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions for text summarization and formatting. It does not request or use any platform tools, shell commands, or network resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user-provided text (articles/blog posts). However, the attack surface is minimal as the skill lacks executable capabilities (no tool access, no file writes, no network calls).
  • Ingestion points: User-provided text in the conversation context as described in SKILL.md.
  • Boundary markers: Not explicitly defined in the SOP for the input text.
  • Capability inventory: No capabilities detected. The skill only outputs text to the user.
  • Sanitization: No specific sanitization or escaping of input content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:11 AM