The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from an external source (vuejs.org), which creates a potential surface for indirect prompt injection attacks.
Ingestion points: Data enters the agent's context through tools like vuejs_org__post_indexes_queries_2 (search results) and unbrowse.scrape (web page content) as described in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters provided to help the agent distinguish between its instructions and the data fetched from the external website.
Capability inventory: The skill provides powerful browser automation and task execution capabilities, such as unbrowse.run and unbrowse.browse.act, which could be targeted by instructions embedded in the external content.
Sanitization: The instructions do not specify any sanitization, filtering, or validation of the content retrieved from vuejs.org before it is presented to the agent.
[EXTERNAL_DOWNLOADS]: The skill establishes a connection to a remote Model Context Protocol (MCP) server to function.
As specified in server.json, the skill uses a streamable-http remote connection to https://unbrowse.ai/mcp/vuejs.org. This resource belongs to the skill's vendor (unbrowse-ai).

vuejs