team-of-one
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a Python script (
scripts/init.py) for scaffolding state files. Technical review of the script shows it performs only local file system operations using standard libraries to create directories and write template markdown content. It does not engage in network activity or unauthorized file access. - [PROMPT_INJECTION]: The instructions within the skill define operational guardrails, such as making decisions with 70% information and following a 'single-thread' focus. These are intended behavioral steering mechanisms for productivity and do not contain patterns typical of malicious prompt injection, such as instructions to ignore safety filters or reveal system prompts.
- [SAFE]: The skill does not contain hardcoded credentials, obfuscated code, or mechanisms for data exfiltration. All external links point to legitimate documentation and official repositories.
Audit Metadata