Skills
Navigate
skills/diegosouzapw/omniroute/omni-agents-a2a/Gen Agent Trust Hub

omni-agents-a2a

Pass

Audited by Gen Agent Trust Hub on Oct 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references a setup configuration hosted on the author's official GitHub repository.
  • Reference URL: https://raw.githubusercontent.com/diegosouzapw/OmniRoute/main/skills/omniroute/SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external API responses, which presents a surface for potential indirect instruction injection.
  • Ingestion points: Responses from the $OMNIROUTE_URL/a2a endpoint (SKILL.md).
  • Boundary markers: None explicitly defined in the examples to delimit API output from agent instructions.
  • Capability inventory: Network communication via curl and JSON-RPC method execution.
  • Sanitization: Not explicitly mentioned in the provided skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 10, 2026, 07:07 PM