a6-plugin-limit-req

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill interacts with the a6 command-line utility to manage Apache APISIX routes and plugin configurations, which is the primary intended functionality.
  • [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection by processing external configuration data through shell command templates.
  • Ingestion points: Plugin configuration fields such as rate, burst, key, and uri defined in SKILL.md examples.
  • Boundary markers: The examples use quoted heredocs (e.g., <<'EOF') which is a security best practice to prevent the local shell from expanding variables within the data block.
  • Capability inventory: The skill is capable of performing a6 route create and a6 route update operations via subprocess execution.
  • Sanitization: While the skill uses quoted heredocs to protect against immediate shell injection, it does not explicitly describe application-level validation for the configuration values themselves.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 02:58 PM