Skills
Navigate
skills/aadi-labs/sikaru-plugins/sikaru-decision/Gen Agent Trust Hub

sikaru-decision

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the sikaru_sdk Python package and the @aadi-labs/sikaru-sdk Node.js package, which are official SDKs from the vendor 'aadi-labs' for interacting with their API.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted text or JSON data ('state') for classification. This is the primary function of the skill. Ingestion points: Data passed to classification commands in SKILL.md. Boundary markers: None specified. Capability inventory: Network access to api.sikaru.ai. Sanitization: Not implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 10:07 AM