deep-research
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes content from arbitrary external websites during the research process.\n
- Ingestion points: Untrusted data enters the agent context via the
firecrawl_scrapeandcrawling_exatools used to retrieve full page content as described inSKILL.md.\n - Boundary markers: The instructions do not define any boundary markers or special delimiters to separate scraped content from the agent's core instructions, nor do they instruct the agent to ignore commands embedded in the data.\n
- Capability inventory: The agent has the capability to write the synthesized research reports to files and can launch subagents for parallel research using the platform's
Tasktool as specified inSKILL.md.\n - Sanitization: There is no evidence of sanitization, filtering, or validation of the retrieved web content before it is interpolated into the agent's context for synthesis.
Audit Metadata