walter-writes-humanizer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (AI-generated text) which could contain hidden instructions designed to influence the agent's behavior. \n
- Ingestion points: Untrusted data enters the agent context through the text provided for humanization (referenced in SKILL.md). \n
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the source text. \n
- Capability inventory: The skill is limited to text rewriting and does not utilize file-system, network, or code execution capabilities. \n
- Sanitization: There is no explicit sanitization or filtering of the input text to remove potential prompt injection attacks.\n- [SAFE]: The skill references the external website walterwrites.ai, which is identified as a legitimate resource belonging to the skill's author.
Audit Metadata