deep-research
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content retrieved from the web which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Web content fetched via firecrawl_scrape and crawling_exa in Step 4.
- Boundary markers: The instructions do not define clear delimiters or 'ignore instructions' wrappers for the data being scraped.
- Capability inventory: The skill can perform file-write operations (Step 6) and launch parallel subagents, which increases the potential impact of a successful injection.
- Sanitization: There is no explicit logic to sanitize or escape the content retrieved from external sources before synthesis.
Audit Metadata