The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Recommends downloading security wordlists from the well-known SecLists repository on GitHub for use in directory enumeration.\n- [COMMAND_EXECUTION]: Provides specific commands for running common security auditing tools such as ffuf and gobuster to identify hidden application paths.\n- [INDIRECT_PROMPT_INJECTION]:\n
Ingestion points: The scripts/agent.py script interacts with external web endpoints, ingesting HTTP response metadata such as status codes and content lengths.\n
Boundary markers: No specific boundary markers or 'ignore' instructions are used for the external data ingested during probing.\n
Capability inventory: The skill utilizes the requests library to perform network probing and creates a local JSON file containing the discovered endpoints.\n
Sanitization: Probing logic relies on metadata evaluation (status codes and size) and does not parse or execute the response body content.

bypassing-authentication-with-forced-browsing