The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted content from external websites to generate intelligence reports, creating a surface for indirect prompt injection.
Ingestion points: The skill retrieves HTML bodies, JSON data, and DOM snapshots from target URLs using proxy_get_session_exchange, proxy_search_session_bodies, and interceptor_browser_snapshot (SKILL.md).
Boundary markers: The instructions lack explicit delimiters or warnings to the agent to ignore potential instructions embedded within the processed web data.
Capability inventory: The agent has the ability to write files (Step 6) and execute a wide range of browser and proxy control tools via the proxy-mcp MCP server.
Sanitization: No sanitization or filtering logic is specified for the data ingested from external sites.
[EXTERNAL_DOWNLOADS]: The documentation provides instructions for installing external dependencies from public registries.
Evidence: README.md recommends installing proxy-mcp via npx from NPM and camoufox via pip. These are well-known package registries and the tools are provided by the skill author (yfe404).

intel-agent