swan-design
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified in the analyzed files. The skill is composed of instructional markdown and reference templates.
- [NO_CODE]: This skill contains no executable scripts (Python, JavaScript, Shell, etc.) and relies entirely on natural language instructions and markdown templates.
- [PROMPT_INJECTION]: Analysis of the instructions revealed no attempts to override agent constraints, bypass safety filters, or extract system prompts. The 'Grove' persona and specific formatting rules (e.g., no em-dashes) are benign instructional constraints.
- [DATA_EXFILTRATION]: The skill does not contain hardcoded credentials, sensitive file path references, or any networking capabilities. There are no calls to external APIs or tools like curl or wget.
- [REMOTE_CODE_EXECUTION]: There are no commands that facilitate external downloads or the execution of remote scripts. All references are local to the skill's file structure.
Audit Metadata