T08 · Insecure Dependencies
- Location
SKILL.md:159- Finding
Automatic Installation and Execution of Unpinned Third-Party Dependencies
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This local memory skill is purpose-aligned, but needs review because it tells an agent to automatically install and run unpinned external code while keeping persistent memories under the user's home directory.
Install only if you are comfortable with a local memory database that persists across sessions and with an agent installing external Python packages and model files. Prefer reviewing or pinning the evrmem package and model source, using a virtual environment, and avoiding storage of secrets or untrusted instructions until the skill documents review and deletion controls.
SKILL.md:159Automatic Installation and Execution of Unpinned Third-Party Dependencies
The skill explicitly supports storing arbitrary user-provided content into persistent semantic memory (Save this to memory / Remember this information). This creates a persistent prompt/context injection surface where malicious or sensitive content can be stored and later retrieved to influence future model behavior or leak data across tasks.
Use this skill when the user asks to:
- "Search memories" or "Find related memories"
- "Save this to memory"
- "Remember this information"
- "Search my knowledge base"
- "Find past notes about X"
The configuration defines a persistent storage location under the user's home directory for memory and settings, enabling information to survive across sessions. In an agent context, session persistence increases the chance of unintended retention of sensitive data, cross-task contamination, and later retrieval of attacker-seeded content.
Create ~/.evrmem/config.yaml:
vector_db:
The skill instructs the agent to run pip install evrmem and evrmem init, which changes the host environment and may download and execute unpinned third-party package code and a large model without explicit user approval. In an agent setting, this is dangerous because it can trigger unauthorized system modifications, supply-chain risk, and unexpected network activity.