humanizer
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. It ingests untrusted text from users and processes it using powerful tools like Read, Write, and Edit. There are no explicit boundary markers or instructions to the agent to ignore commands embedded within the text provided for humanization. An attacker could provide text that includes instructions to manipulate files or leak information.
- Ingestion points: User-provided text passed to the skill for processing in SKILL.md.
- Boundary markers: None present in the skill's instructions to separate user data from instructions.
- Capability inventory: The skill is granted access to the Read, Write, Edit, Grep, Glob, and AskUserQuestion tools.
- Sanitization: No sanitization or validation of the input text is performed before the agent processes it.
Audit Metadata