audit-before-i-publish

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted content drafts provided by users, which serves as an attack surface for indirect prompt injection instructions.
  • Ingestion points: User-provided drafts submitted for auditing (SKILL.md).
  • Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore embedded commands within the drafts.
  • Capability inventory: Utilizes tools such as get_voice_profile, score_voice_match, improve_post, and publish_post (SKILL.md).
  • Sanitization: Absent; no specific validation or escaping mechanisms for the input text are described.
  • [COMMAND_EXECUTION]: The skill provides detailed instructions for the agent to execute specific tool functions related to the VoiceMoat service.
  • Evidence: Procedural steps for calling tools like publish_post are documented, notably including a strong safety requirement for human-in-the-loop confirmation before completion (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 07:23 AM