i-have-adhd
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to intercept and format the agent's response to all user communications ("Use this skill whenever responding to ANY user message"), which exposes it to indirect prompt injection if user-provided content contains instructions to deviate from the formatting rules.
- Ingestion points: Processes all user-supplied messages including coding tasks, debugging, and casual conversation.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the user input.
- Capability inventory: The skill itself does not define any tools, shell commands, or network operations.
- Sanitization: No sanitization or validation of the processed user data is implemented within the instructions.
Audit Metadata