tech-entrepreneur-coach-adhd
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it can fetch untrusted data from the internet and subsequently perform file operations.
- Ingestion points: The skill utilizes tools such as
mcp__firecrawl__firecrawl_search,mcp__brave-search__brave_web_search, andWebFetchto retrieve content from external URLs (file: SKILL.md). - Boundary markers: There are no explicit instructions or delimiters in the prompt to prevent the agent from executing instructions that might be hidden within the fetched web content.
- Capability inventory: The agent has access to
Write,Edit, andTodoWritetools, which grant it the ability to create or modify files on the host system (file: SKILL.md). - Sanitization: No validation, escaping, or filtering of the external data is performed before the agent processes the information and uses its file-writing capabilities.
Audit Metadata