content-model

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of untrusted user input during the content modeling discovery phase.
  • Ingestion points: The agent gathers business requirements and content needs through a series of discovery questions defined in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the user's answers strictly as data or to ignore any embedded instructions within that content.
  • Capability inventory: The skill instructs the agent to use these requirements to generate a structured mass operations JSON file and then validate it using the build-mass-operation MCP tool. This combination of processing untrusted input and generating platform configuration payloads creates a potential injection surface.
  • Sanitization: The instructions lack guidance on sanitizing or escaping the user-provided content before it is interpolated into the generated JSON schema definitions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 12:02 PM
Security Audit — agent-trust-hub — content-model