methodology

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies and interprets development guidance from methodology files located in the .standards/methodologies/ directory. These YAML files can include custom prompts designed to influence the agent's behavior during specific development phases.
  • Ingestion points: .standards/methodologies/*.methodology.yaml (as described in create-methodology.md and runtime.md)
  • Boundary markers: No explicit boundary markers or delimiters for the guidance content are identified.
  • Capability inventory: The skill is allowed to use Read, Write, Grep, and Glob tools.
  • Sanitization: No explicit validation or sanitization of the guidance prompt content is documented.
  • [EXTERNAL_DOWNLOADS]: The skill references a methodology schema hosted in the Anthropics official GitHub repository for validating workflow configurations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 09:14 PM