complexity-guard

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its core workflow of processing external design files.
  • Ingestion points: The skill reads untrusted data from various local file paths such as 'genesis/v{N}/02_ARCHITECTURE_OVERVIEW.md' using the 'view_file' tool.
  • Boundary markers: There are no instructions or delimiters provided to the agent to isolate the audited content from the system instructions, allowing potential embedded commands to influence agent behavior.
  • Capability inventory: The skill has the capability to write files to the disk using the 'write_to_file' tool, which could be exploited to save malicious content if the audit process is subverted.
  • Sanitization: The skill does not perform any validation, escaping, or filtering of the content read from external files before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 07:05 PM