humanizer
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing untrusted text while possessing broad file system permissions.
- Ingestion points: Untrusted data enters the agent context through the text provided to the agent for 'humanization' as described in SKILL.md.
- Boundary markers: Absent. The instructions do not specify any delimiters or warnings to ignore embedded instructions within the input text.
- Capability inventory: The skill has access to powerful file system and interaction tools, including Read, Write, Edit, Grep, Glob, and AskUserQuestion (as listed in the SKILL.md allowed-tools section).
- Sanitization: Absent. There is no mechanism described to sanitize, escape, or filter instructions that might be maliciously embedded in the text being processed.
Audit Metadata