retention-specialist
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill primarily serves as a compatibility layer for legacy prompts and defines a set of rigorous operational protocols for the agent framework. These protocols emphasize security best practices such as least privilege, TDD gating, and PII redaction.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface where untrusted data enters the agent context via web content (BrowserOS). It addresses this by providing instructions to treat external data as hostile and to redact secrets and PII before sharing context. The agent has capabilities for terminal execution (rtk) and persistent storage (Obsidian), but the skill mandates sanitization and defensive handling of external content.
- [COMMAND_EXECUTION]: The framework utilizes a command execution proxy (rtk) for development tasks such as running tests. This follows a structured approach to execution rather than arbitrary shell access.
Audit Metadata