ktx-ai-data-agents-mcp-context-skills

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions require the installation of the @kaelio/ktx package from the public npm registry. This introduces an external dependency into the agent environment.
  • [COMMAND_EXECUTION]: The skill documentation includes an Advanced Usage section with a TypeScript example that uses child_process.exec to run shell commands. The pattern ktx sl ${query} --json is vulnerable to command injection if the query variable contains unsanitized user input.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill ingests context from untrusted external sources such as Notion, dbt projects, and Confluence as described in SKILL.md.
  • Boundary markers: No specific boundary markers or ignore instructions are present to delimit external data from agent instructions.
  • Capability inventory: The skill exposes capabilities for searching wikis and semantic layers, allowing the agent to process data from these sources.
  • Sanitization: The instructions do not describe any sanitization or validation of the external content before it is processed by the AI agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 10:43 PM
Security Audit — agent-trust-hub — ktx-ai-data-agents-mcp-context-skills