overseer
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a documentation and implementation guide for the Overseer task management system. It provides structured methods for tracking multi-session work without introducing security vulnerabilities.
- [COMMAND_EXECUTION]: The skill documents automated version control system (VCS) operations, such as creating bookmarks and committing changes using tools like Git or Jujube (jj). These operations are restricted to the tool's core functionality of task tracking and do not allow for arbitrary command injection.
- [DATA_EXFILTRATION]: Persistence is managed through a local SQLite database. The analysis confirmed that the skill does not contain hardcoded credentials, sensitive file path access, or unauthorized network operations to external domains.
- [PROMPT_INJECTION]: The skill facilitates the ingestion of task descriptions and implementation contexts. While this represents a data ingestion surface common to task management tools, it does not provide methods to bypass core agent safety protocols or execute high-risk operations based on untrusted data.
Audit Metadata