The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from the web, which creates a surface for indirect prompt injection attacks.
Ingestion points: External content is ingested via firecrawl_scrape and crawling_exa in SKILL.md (Step 4).
Boundary markers: The instructions do not specify explicit delimiters or boundary markers to isolate scraped content from the agent's instructions.
Capability inventory: The skill has the capability to synthesize reports, save results to files, and launch parallel subagents using the Task tool (Step 6 and Parallel Research section).
Sanitization: The skill includes 'Quality Rules' to prevent hallucination and prioritize reputable sources, but does not specify technical sanitization or escaping of the ingested web content.

deep-research