wdyt
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user input through the $ARGUMENTS variable in SKILL.md. \n
- Ingestion points: User input provided via the /wdyt command is interpolated into the prompt text in SKILL.md.\n
- Boundary markers: The skill does not utilize explicit delimiters or markers to isolate user-provided arguments from the instructions.\n
- Capability inventory: No file system access, network operations, or command execution capabilities are utilized by this skill.\n
- Sanitization: The skill does not perform sanitization on the input before interpolation.\n- [SAFE]: The skill uses natural language instructions to define a specific persona. The referenced GitHub repository is owned by the author and used for attribution purposes. No suspicious code or obfuscation was found.
Audit Metadata