postfix-billionmail
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze mail server logs, transport maps, and configuration files, which represent sources of external and potentially untrusted data.
- Ingestion points: Workflow steps 4 and 8 involve tracing messages through logs and inspecting container mounts. Step 6 involves reading various Postfix configuration files and maps.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore instructions that might be embedded within mail headers or log entries.
- Capability inventory: The skill is authorized to capture system configuration (
postconf -n) and modify persistent configuration sources. - Sanitization: No specific data sanitization or escaping mechanisms are mentioned for handling external content before it is processed by the agent.
Audit Metadata