The Agent Skills Directory

[SAFE]: The skill instructions define a legitimate research workflow focused on data synthesis and source attribution. It uses well-known MCP tools for web interaction.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from the web. Ingestion points: External web page content fetched via firecrawl_scrape and crawling_exa (SKILL.md). Boundary markers: The instructions do not specify any delimiters or safety headers to separate retrieved content from agent instructions. Capability inventory: The skill utilizes network search and scraping tools, and includes a step to save reports to local files (SKILL.md). Sanitization: No explicit content sanitization or validation logic is present.
[NO_CODE]: The skill consists entirely of markdown instructions and does not include any standalone scripts or executable files.

deep-research