The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from external websites to generate comprehensive audit reports.
Ingestion points: Untrusted data enters the agent context when fetching content from target URLs, including robots.txt, llms.txt, and general page content via WebFetch or curl.
Boundary markers: The instructions lack explicit boundary markers or directives for the agent to disregard instructions that may be embedded within the fetched third-party data.
Capability inventory: The skill possesses capabilities to execute shell commands (Bash), perform network requests (WebFetch), and write to the local file system (Write).
Sanitization: There are no defined procedures for sanitizing or escaping the external content before it is interpolated into the prompts for report generation.
[COMMAND_EXECUTION]: The skill documentation and examples demonstrate the use of the Bash tool to perform network operations and suggests the use of external utilities for report formatting.
Evidence: The How to Use and Example sections reference using curl to interact with remote targets, and the compatibility notes mention requirements for pandoc and headless Chrome for PDF generation.

geo-report