postwall
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill package contains only a manifest and markdown documentation. No executable logic, scripts, or binaries are provided within the skill files.
- [PROMPT_INJECTION]: The skill's stated purpose involves processing external email content, which presents a surface for indirect prompt injection. However, the skill explicitly incorporates human-in-the-loop approval as a security control.
- Ingestion points: Incoming email content (SKILL.md).
- Boundary markers: None explicitly defined in the provided metadata.
- Capability inventory: Reading and sending emails.
- Sanitization: Relies on human-in-the-loop approval rather than automated sanitization in the metadata.
Audit Metadata