The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external websites using tools like web_fetch and browser automation. This creates a surface for indirect prompt injection attacks where malicious instructions embedded in scraped content could attempt to influence the agent's behavior.
Ingestion points: Data retrieved from external URLs via web_fetch and browser tools as described in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore instructions found within the scraped content.
Capability inventory: The skill utilizes web fetching, browser automation, and file writing to the local workspace for storing results.
Sanitization: No specific sanitization or filtering of the retrieved content is mentioned in the extraction workflow.

web-scraping