skills/mukul975/anthropic-cybersecurity-skills/implementing-google-workspace-phishing-protection/Gen Agent Trust Hub
implementing-google-workspace-phishing-protection
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/agent.pyexecutes the Google Apps Manager (GAM) command-line tool usingsubprocess.run. This is an expected behavior for the skill's purpose of auditing GWS settings, and the implementation uses argument lists to prevent shell injection. - [DATA_EXPOSURE_EXFILTRATION]: The script
scripts/process.pyperforms DNS lookups to verify the presence and correctness of email authentication records. These network operations are limited to public DNS queries required for auditing and do not involve the transmission of sensitive data to external servers. - [INDIRECT_PROMPT_INJECTION]: The auditing scripts ingest external data from JSON configuration files and DMARC reports. While this represents a surface for indirect prompt injection where malicious data could affect the audit results, the risk is mitigated by the structured nature of the data and is necessary for the skill's primary function.
Audit Metadata