skills/simota/agent-skills/rank/Gen Agent Trust Hub

rank

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is documentation-only and contains no executable code or scripts. It explicitly defines a boundary against writing or modifying code.
  • [NO_CODE]: No executable files, scripts, or package dependencies are present in the skill.
  • [EXTERNAL_DOWNLOADS]: The skill references methodology sources from well-known platforms (Nature, arXiv, Intercom). These are informational links for human/agent context and do not involve code execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted item descriptions for scoring, representing a potential surface for indirect prompt injection. However, since the skill has no destructive capabilities (no network, no file-write, no shell), this surface is assessed as safe. * Ingestion points: Item attributes in the COLLECT phase (SKILL.md). * Boundary markers: None explicitly defined. * Capability inventory: None (no-code skill). * Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:06 PM