email-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill retrieves and processes untrusted data from email subjects, sender names, and recipient lists, which could potentially contain instructions aimed at the agent.
- Ingestion points: Email metadata (Subject, Sender Name, Recipient Name) retrieved via the
workiq-asktool inSKILL.md(Step 2 and Step 3). - Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard potential commands embedded within the email data.
- Capability inventory: The skill primarily uses formatting and computation capabilities; no high-risk capabilities like file system writes or network exfiltration tools are requested or used within the skill's defined workflow.
- Sanitization: The skill does not define specific sanitization or escaping protocols for the external content before it is interpolated into the final dashboard output.
Audit Metadata