cowork
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [PROMPT_INJECTION] (SAFE): The instructions consist of behavioral guidelines and professional etiquette rules. There are no attempts to bypass safety filters, override system prompts, or extract internal instructions.
- [DATA_EXFILTRATION] (SAFE): The skill does not contain network request code (curl, wget) or references to sensitive system files (SSH keys, AWS credentials).
- [COMMAND_EXECUTION] (SAFE): No shell commands or executable scripts are present in the skill.
- [INDIRECT_PROMPT_INJECTION] (SAFE): The skill defines patterns for interacting with local directories like
vault/andplanning/. However, it does not include any tools or code that could be used to exploit malicious content found in those files, such as network exfiltration or command execution capabilities. - [REMOTE_CODE_EXECUTION] (SAFE): No external dependencies or remote script downloading patterns were identified.
Audit Metadata