cybiq-cra-scope

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves configuration files and legal data from https://cybiq.eu, including OpenAPI specifications, offer listings, and decision dictionaries. These resources are necessary for the skill to provide accurate, up-to-date information regarding EU regulations.
  • [COMMAND_EXECUTION]: The instructions contain curl command templates for the agent to use when interacting with the Cybiq API. These commands are restricted to the service's API endpoints and do not involve executing untrusted scripts or piping remote content to the shell.
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches data from external sources such as llms.txt and classification API responses, which constitutes an ingestion surface for untrusted data.
  • Ingestion points: Remote resources hosted at https://cybiq.eu/llms.txt and https://cybiq.eu/api/classify.
  • Boundary markers: The skill does not explicitly define delimiters to isolate external content within the prompt context.
  • Capability inventory: The skill's capabilities are focused on network communication with the vendor's API.
  • Sanitization: There is no evidence of explicit sanitization or filtering of instruction-like content in the API responses.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 09:58 AM
Security Audit — agent-trust-hub — cybiq-cra-scope