health
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill sources a local identity resolver script (_identity.sh) from a path determined by environment variables.
- [COMMAND_EXECUTION]: Executes a Python command to validate the JSON format of a temporary session statistics file in /tmp/.
- [DATA_EXFILTRATION]: Accesses the MEM0_API_KEY environment variable and displays the first six characters for diagnostic confirmation.
- [DATA_EXFILTRATION]: Reads local vendor configuration files such as ~/.mem0/project_map.json to resolve project identifiers.
- [PROMPT_INJECTION]: The 'Memory Quality Analysis' feature creates a surface for indirect prompt injection by processing external memory data.
- Ingestion points: Retrieves existing memories via get_memories for duplication and contradiction analysis.
- Boundary markers: No delimiters or instructions are used to ignore potentially malicious content within the retrieved memories.
- Capability inventory: The skill is capable of adding and deleting memories, sourcing scripts, and executing system commands.
- Sanitization: The skill does not perform sanitization or validation of the memory content before textual comparison.
Audit Metadata