research-brief
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the internet using WebSearch, WebFetch, Firecrawl, and Exa to produce research briefs.\n
- Ingestion points: Content fetched from external URLs via WebFetch and Firecrawl scrape (SKILL.md, references/mcp-probe.md).\n
- Boundary markers: The instructions do not specify explicit delimiters or warnings for the agent to ignore instructions embedded within the fetched content.\n
- Capability inventory: The skill has Write permissions to the local filesystem and Bash access (SKILL.md).\n
- Sanitization: There is no explicit logic described for sanitizing or filtering malicious prompt injection patterns within the fetched research data.\n- [EXTERNAL_DOWNLOADS]: The skill references and recommends the installation of external tools such as Firecrawl (github.com/firecrawl/firecrawl-mcp) and Exa MCPs to enhance research capabilities (references/mcp-probe.md). These are well-known services.
Audit Metadata