The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from live websites which constitutes an Indirect Prompt Injection surface. * Ingestion points: The skill uses browser_navigate to load external URLs and inventories DOM elements and network responses in SKILL.md. * Boundary markers: No specific delimiters or instructions to ignore embedded malicious prompts within the audited pages are provided. * Capability inventory: The agent can perform click and submit actions via Playwright and execute shell commands for database queries as described in SKILL.md. * Sanitization: No explicit sanitization or filtering of the external website content is described.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell-based database clients such as psql, mysql, mongosh, and wrangler to verify data integrity.
[CREDENTIALS_UNSAFE]: The skill requests and handles authentication details and database connection strings from the user at runtime to perform its audit tasks.

mock-hunter