remove-ai-tells
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process text provided by users for editing, which introduces a standard surface for indirect prompt injection attacks.
- Ingestion points: The skill accepts "The text" from the user as the primary input for its humanization logic (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters (such as XML tags or unique markers) to isolate untrusted user text from the agent's internal instructions.
- Capability inventory: The skill includes instructions to interface with external tools like the "Scratchpad connector" or other notes tools to save, create, or replace content.
- Sanitization: There are no explicit instructions to sanitize or validate the user-provided text before the agent processes or saves it.
- [NO_CODE]: The skill consists entirely of Markdown-based instructions for the agent and does not include any scripts, executables, or binary files.
Audit Metadata