coralogix-docs

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes documentation content fetched from an external source to answer user queries, which represents a surface for indirect prompt injection.
  • Ingestion points: Document content is retrieved from coralogix.com/docs using the cx docs fetch command.
  • Boundary markers: The instructions do not define specific delimiters to isolate fetched content from the rest of the prompt.
  • Capability inventory: The skill's capabilities are limited to searching and fetching documentation via the cx CLI tool.
  • Sanitization: The skill treats content from the official documentation domain as authoritative.
  • [EXTERNAL_DOWNLOADS]: Fetches documentation pages in markdown format from the official coralogix.com domain.
  • [COMMAND_EXECUTION]: Utilizes the cx docs search and cx docs fetch commands from the Coralogix CLI to interact with the documentation service.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 09:44 PM
Security Audit — agent-trust-hub — coralogix-docs