The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill is designed to ingest and process data from external websites, which is a classic surface for indirect prompt injection attacks. Evidence Chain: 1. Ingestion points: External website content retrieved via Apify actors (SKILL.md). 2. Boundary markers: Absent; there are no instructions for the agent to use delimiters or ignore embedded instructions within the scraped data. 3. Capability inventory: Execution of Apify actors and network access for data acquisition. 4. Sanitization: Absent; no specific cleaning or filtering of the scraped content is mandated before the agent processes it.

mcp-apify