report-distribution-agent
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill architecture creates an indirect prompt injection surface by processing untrusted data to trigger network-based side effects.
- Ingestion points: The agent receives input from the
run.shtask arguments and consolidated data from a separate 'Data Consolidation Agent' as specified in the workflow. - Boundary markers: The instructions in
SKILL.mddo not include delimiters or specific guidance for the agent to distinguish between its core instructions and potentially malicious content embedded in the sales data it processes. - Capability inventory: The agent is empowered to format HTML reports and transmit them externally via SMTP transport, which could be exploited if instructions are injected into the report data.
- Sanitization: The workflow description lacks explicit steps for validating or escaping the consolidated sales data before it is interpolated into the HTML email templates.
Audit Metadata