agent-qa-authoring

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides fallback instructions to use 'npx --yes agent-qa ids generate'. The '--yes' flag automatically accepts installation prompts, resulting in the download and execution of the package from the npm registry.
  • [COMMAND_EXECUTION]: The workflow instructs the agent to execute shell commands using the 'agent-qa' CLI for ID generation and validation when MCP tools are unavailable.
  • [EXTERNAL_DOWNLOADS]: The skill's fallback mechanisms involve downloading the 'agent-qa' package from the public npm registry.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external workspace configurations and test definitions, creating a potential surface for indirect injection if these sources are compromised. Ingestion points: Discovery of workspace structures and configuration retrieval. Boundary markers: Explicit user confirmation is required for destructive operations. Capability inventory: File system modification, shell command execution, and test enqueuing. Sanitization: Relies on specific validation tools to ensure schema integrity.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 10:16 AM
Security Audit — agent-trust-hub — agent-qa-authoring