wfgy-method

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements a 'durable lessons' mechanism that maintains state across sessions by reading from a project-local file (.wfgy/lessons.md), which creates a surface for indirect prompt injection if the local environment is influenced by untrusted data.
  • Ingestion points: The instructions direct the agent to read the .wfgy/lessons.md file at the start of every new task within the project to inherit prior reasoning lessons.
  • Boundary markers: The instructions do not specify the use of clear delimiters or explicit instructions to treat the file content as non-executable data when incorporating it into the current task context.
  • Capability inventory: The skill has the capability to perform file system operations (read and write) and interacts with project-local tools (a similarity check verb) to monitor reasoning drift.
  • Sanitization: There is no mention of sanitizing or validating the content of the lessons file before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 01:16 AM
Security Audit — agent-trust-hub — wfgy-method