skills/kyoji2/sosumi-skill/sosumi/Gen Agent Trust Hub

sosumi

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [NO_CODE]: The skill is composed exclusively of configuration and instructional markdown files and does not contain any executable scripts.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation from the external service 'sosumi.ai', including arbitrary HTTPS URLs.
  • [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface. Ingestion points: Data is retrieved from 'sosumi.ai' and external HTTPS URLs. Boundary markers: There are no instructions to delimit or ignore instructions within the fetched content. Capability inventory: No code execution capabilities are present in the skill files. Sanitization: Content is processed as-is without filtering or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 09:13 AM