The Agent Skills Directory

[PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from X.com, which could contain malicious instructions.\n- Ingestion points: Data is extracted using the mcp__claude-in-chrome__read_page tool as described in SKILL.md.\n- Boundary markers: The instructions do not include markers or warnings to distinguish between navigation commands and untrusted page content.\n- Capability inventory: The skill allows access to browser automation (mcp__claude-in-chrome__*), Read, and Write tools.\n- Sanitization: No sanitization or validation logic is defined for the data gathered from the website.\n- [NO_CODE]: The skill contains only instructional text in markdown and does not bundle any scripts or executable code.

x-navigation