expertise-file-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- PROMPT_INJECTION (SAFE): No instructions attempting to override agent constraints or bypass safety filters were detected.
- DATA_EXFILTRATION (SAFE): No network operations, hardcoded credentials, or sensitive file path access patterns were found.
- REMOTE_CODE_EXECUTION (SAFE): The skill does not download or execute remote scripts and contains no package management files.
- NO_CODE (SAFE): The skill consists exclusively of markdown documentation and YAML templates without any executable scripts or binary files.
- INDIRECT_PROMPT_INJECTION (SAFE): Although the skill provides templates for data the agent will read, it does not involve untrusted data interpolation or missing boundary markers that would facilitate injection.
Audit Metadata