methodology

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references a methodology YAML schema hosted on the official Anthropics GitHub repository, which is a trusted source.
  • [PROMPT_INJECTION]: The skill implements an Indirect Prompt Injection surface by ingesting and interpreting instructions from project-specific configuration files.
  • Ingestion points: The agent reads custom instructions from the guidance.prompt field within .standards/methodologies/*.methodology.yaml files.
  • Boundary markers: No explicit boundary markers or 'ignore' instructions are used when interpolating these custom prompts into the active agent session.
  • Capability inventory: The skill is granted Read and Write permissions via the allowed-tools configuration, enabling it to modify project files and source code based on instructions from these methodology files.
  • Sanitization: There is no evidence of validation or sanitization of the content provided in the custom methodology prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 03:38 PM