voice-builder

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Vulnerability to indirect prompt injection via untrusted data processing.\n
  • Ingestion points: Writing samples provided by the user for analysis (referenced in SKILL.md, Step 1 and samples-guide.md).\n
  • Boundary markers: Absent; the instructions do not require the use of delimiters or specific safety instructions to disregard commands embedded within input samples.\n
  • Capability inventory: The skill reads from brand-profile.md and writes to voice.md (SKILL.md, Steps 0 and 4).\n
  • Sanitization: No sanitization, validation, or filtering of the content within writing samples is described or required.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 06:02 PM
Security Audit — agent-trust-hub — voice-builder