curriculum-package-web

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION] (SAFE): The skill instructions in SKILL.md are purely descriptive and do not contain any patterns intended to bypass safety filters or override agent instructions.
  • [DATA_EXFILTRATION] (SAFE): No network operations (curl, wget, requests) or access to sensitive file paths (e.g., ~/.ssh, .env) were detected. The skill only performs string manipulation on the provided content path.
  • [REMOTE_CODE_EXECUTION] (SAFE): There are no patterns involving the download and execution of remote scripts. The Python code uses standard library imports and a local framework reference.
  • [COMMAND_EXECUTION] (SAFE): While the documentation mentions a CLI interface, the actual Python implementation does not use subprocess.run, os.system, or any other method to execute shell commands.
  • [INDIRECT_PROMPT_INJECTION] (SAFE): The skill accepts a 'content_path' as input but only uses its filename 'stem' for metadata reporting. It does not ingest or process the contents of external files, eliminating the surface for indirect injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:17 PM