author-governance-ruleset

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill performs an automated installation of the 'mulesoft-anypoint-cli-governance-plugin' using the Anypoint CLI. This is a standard operation for vendor-provided tooling and ensures the environment matches the skill requirements.
  • [COMMAND_EXECUTION]: The 'Bash' tool is utilized to execute 'anypoint-cli-v4' commands for discovering API models, resolving business terms, and validating YAML ruleset files.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates user-controlled strings directly into shell commands. Ingestion points: User-provided terms, domain names, and class names used in CLI arguments throughout Step 1, 2, 3, and 4 in SKILL.md. Boundary markers: No delimiters or instructions are provided to the agent to treat this data as untrusted. Capability inventory: The 'Bash' tool is enabled, allowing execution of the interpolated commands. Sanitization: The instructions do not specify any input validation, escaping, or sanitization logic for the user-supplied values before they are passed to the shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 09:01 AM
Security Audit — agent-trust-hub — author-governance-ruleset