life-planning
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No malicious override instructions or jailbreak attempts were found. The language is purely instructional for the agent's task.
- [Data Exposure & Exfiltration] (SAFE): While the skill references local file paths (e.g., .claude/memories, my-vault/), there are no hardcoded credentials or commands that transmit this data to external servers.
- [Remote Code Execution] (SAFE): No remote code patterns, shell commands, or external script downloads are present.
- [Obfuscation] (SAFE): No encoded strings, hidden characters, or homoglyphs were detected.
- [Indirect Prompt Injection] (LOW): The skill directs the agent to read data from various local directories. While these directories could contain untrusted data if populated by external sources, the skill itself provides no mechanisms for data transmission or command execution.
Audit Metadata