skills/mem0ai/mem0/policy/Gen Agent Trust Hub

policy

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local Python helper script parse_mem0_config.py located within the $CLAUDE_PLUGIN_ROOT/scripts/ directory to read configuration values. This is an internal execution pattern within the plugin's managed environment.
  • [DATA_EXFILTRATION]: The skill accesses and modifies the mem0.md file in the current working directory to store memory policies. There is no evidence of data being transmitted to external servers or access to sensitive system files beyond the project's own configuration.
  • [PROMPT_INJECTION]: The skill implements an indirect prompt injection surface as its primary function. Ingestion points: User-supplied text via subcommands in SKILL.md. Boundary markers: Explicit Markdown headers (## Instructions) are used to delimit policy content in mem0.md. Capability inventory: The skill can write files and execute a local helper script. Sanitization: No explicit sanitization or filtering is performed on the user-provided policy text. This surface is considered safe as it is the core purpose of the tool and requires direct user interaction.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 05:36 PM
Security Audit — agent-trust-hub — policy