qq-mail-reader
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted email content which serves as an ingestion point for indirect prompt injection.
- Ingestion points: Email bodies and headers are retrieved from the IMAP server and added to the agent's context in SKILL.md.
- Boundary markers: No specific delimiters or instructions are used to distinguish external email content from agent instructions.
- Capability inventory: The skill grants the agent search and read access to the user's mailbox.
- Sanitization: HTML tags are stripped using regex in the get_text_body function, but the resulting plain-text is not sanitized for potential command injections or malicious instructions.
- [SAFE]: The skill uses well-known service endpoints (imap.qq.com) and manages sensitive credentials through standard environment variable and configuration file practices.
Audit Metadata