firecrawl-common-errors
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes HTTP error responses and error strings from the Firecrawl API. While this involves untrusted data ingestion, the instructions emphasize redaction of evidence and use specific boundary markers for diagnostic output. The skill lacks network tools to exfiltrate data, and its capabilities are limited to local file inspection and editing, minimizing the risk of exploitation.
- [DATA_EXPOSURE]: The skill includes explicit security guidelines prohibiting the printing, committing, or transmission of API keys. It recommends the use of approved secret managers for handling credentials and requires redaction of request shapes and IDs in output to prevent accidental exposure of sensitive environment details.
- [EXTERNAL_DOWNLOADS]: The skill references official Firecrawl documentation and GitHub repositories for troubleshooting. These are well-known, legitimate sources for API references and do not involve the execution of untrusted remote code or scripts.
Audit Metadata