The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from arbitrary external websites (as seen in SKILL.md, discovery/autonomous-discovery.md, and various site-pattern playbooks). This ingestion of external HTML, JSON, and documents represents a potential surface for indirect prompt injection, where malicious instructions embedded in scraped content could attempt to influence the agent's behavior. The skill possesses extensive capabilities, including network operations, file system writes, and browser automation (e.g., browser-automation/browser-techniques.md). While it encourages a 'bronze-first' approach for auditing raw data, the provided code snippets do not include explicit input sanitization or strict boundary markers for all extraction paths.

webscraping-expert