Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- INSTALL.md:45
Security audit
Security checks across malware telemetry and agentic risk
The skill is a disclosed persistent-memory tool, but it relies on unreviewed external code and directs agents to automatically store and reuse long-term facts, including possible secrets, without clear user control.
Review this carefully before installing. Use it only if you want persistent cross-session memory, inspect the external package before running its Python scripts, configure what may be stored, and avoid saving API keys or passwords until encryption, deletion, and retention controls are clear.
65/65 vendors flagged this skill as clean.
Detected: suspicious.prompt_injection_instructions