firecrawl-market-research
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection via the processing of untrusted external content.
- Ingestion points: The workflow relies on Firecrawl to search and scrape external web pages, including news, investor relations pages, and financial portals.
- Boundary markers: The instructions lack clear delimiters or system-level warnings to distinguish between the skill's instructions and the data retrieved from external sources.
- Capability inventory: The skill utilizes browser interaction, sub-agents, and parallel task runners, which could be exploited if malicious instructions are encountered on a scraped website.
- Sanitization: There is no evidence of filtering, escaping, or validation of the content retrieved from the internet before it is processed by the agent.
Audit Metadata