course-builder

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an architecture susceptible to indirect prompt injection by combining data ingestion with sensitive capabilities.
  • Ingestion points: The skill gathers course metadata, prerequisites, and outcomes directly from user input (Step 1) and reads local project configuration files (e.g., docs/project-config.json).
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to isolate untrusted user data from the instruction context.
  • Capability inventory: The skill is authorized to write new markdown files to the 'docs/knowledge/courses/' directory and to spawn sub-agents via 'spawn_agent' to execute tasks.
  • Sanitization: The instructions do not include any steps for validating, filtering, or escaping user-provided content before it is interpolated into files or passed to sub-agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 01:53 PM