save-thread
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides documentation and templates for creating session handoffs using the vendor's official CLI tool (nmem) and official documentation links. No malicious patterns such as data exfiltration, persistent access, or obfuscation were identified.\n- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of handoffs by interpolating text into command arguments, which represents a potential attack surface for indirect instructions.\n
- Ingestion points: Session summaries and titles are ingested into the nmem command template in SKILL.md.\n
- Boundary markers: The command template uses double quotes for shell arguments.\n
- Capability inventory: Uses the nmem tool for data creation and storage.\n
- Sanitization: No explicit sanitization or filtering of the interpolated text is defined in the instructions.
Audit Metadata