marketing-reply-drafter

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or dangerous commands were detected in the skill logic or style guides.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it processes untrusted data from social media posts.
  • Ingestion points: The user-provided post text processed in SKILL.md.
  • Boundary markers: None identified in the workflow to delimit user input from instructions.
  • Capability inventory: The skill is limited to drafting text and invoking a writing:humanizer tool; it has no capabilities for network access or file system modification.
  • Sanitization: No validation or sanitization is performed on the input post data.
  • Note: The risk is minimal as the skill's capabilities are restricted and intended for content generation only.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 04:14 PM
Security Audit — agent-trust-hub — marketing-reply-drafter