The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted URLs from command-line arguments and input files. While this creates a surface for indirect prompt injection, it is fundamental to the skill's utility as a security analysis tool. Ingestion points are located in scripts/agent.py and scripts/process.py. Capabilities include network requests to specific security service domains and local file output. No sanitization or boundary markers are implemented for the processed URLs.
[SAFE]: No malicious patterns, unauthorized access, or persistence mechanisms were found. The skill employs secure credential management for API keys and restricts operations to well-known security domains.

analyzing-malicious-url-with-urlscan