sound-less-like-ai

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided text to identify and remove "AI tells," creating an attack surface where malicious instructions embedded in the input could potentially influence agent behavior.
  • Ingestion points: Processes user-provided text drafts for analysis and rewriting as defined in Step 1 of SKILL.md.
  • Boundary markers: The instructions do not define delimiters (such as triple quotes or XML tags) to isolate user content, nor do they instruct the agent to ignore instructions found within the analyzed text.
  • Capability inventory: The skill mentions integration with external tools like get_voice_profile and score_voice_match for advanced voice matching.
  • Sanitization: No input validation or filtering of the text being processed is specified in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 07:23 AM