monica
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a legitimate utility for managing personal CRM data. It does not contain any malicious code, obfuscation, or unauthorized data access patterns.
- [CREDENTIALS_UNSAFE]: The skill correctly handles authentication by using environment variables (
MONICA_API_TOKEN) or a configuration file (~/.config/monica-api/.env) with recommended permissions (chmod 600). It avoids hardcoding secrets and provides a template for users. - [COMMAND_EXECUTION]: The main script (
scripts/monica) is written using only the Python standard library. It does not invoke arbitrary shell commands or spawn untrusted subprocesses. The logic is focused on structured API interactions. - [EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads of code or executable scripts. All network activity is directed toward the user's Monica CRM instance for legitimate data management.
- [DATA_EXFILTRATION]: There is no evidence of data exfiltration. The script communicates exclusively with the Monica API endpoint provided by the user in the configuration.
- [PROMPT_INJECTION]: The
SKILL.mdfile contains clear instructions for the agent, including mandatory human confirmation for destructive actions like deleting contacts or notes, which mitigates the risk of accidental or malicious data loss.
Audit Metadata