The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill suggests installing an external CLI tool via npm install -g adhd-agent and references a GitHub repository at https://github.com/UditAkhourii/adhd. These resources are managed by a user account that does not match the skill's author (sarthib7).
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface because it processes untrusted user input which is then interpolated into instructions for sub-agents. * Ingestion points: User-provided problem description (P) and context. * Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are present. * Capability inventory: The skill utilizes Agent/Task tool calls to execute multiple parallel sub-agent instances. * Sanitization: No sanitization, escaping, or validation of user-provided content is performed before interpolation into the sub-agent prompts.

adhd