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
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:05 AM
Security Audit — agent-trust-hub — postwall