email-parser
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to parse email content, which constitutes untrusted external data. Because the skill is granted access to powerful system tools such as
Bash(cmd:*),Write, andEdit, it creates a vulnerability surface where malicious instructions embedded in parsed emails could potentially be executed by the agent. - Ingestion points: Processes external email data as described in the skill's primary purpose (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined in the skill instructions.
- Capability inventory: Access to
Bash(cmd:*),Write, andEdittools provides a significant execution surface (SKILL.md). - Sanitization: There are no specified sanitization or validation routines for the external text being parsed.
- [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or persistence mechanisms was found in the skill's static instructions.
Audit Metadata