firecrawl-developer-search
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources such as GitHub issues, pull requests, and public documentation. This data is untrusted and could contain malicious instructions or hidden prompts intended to influence the agent's actions during content processing.
- Ingestion points: Search results from
firecrawl_developer_searchand CLI output. - Boundary markers: The skill does not define specific delimiters or instructions for the agent to treat external passages as untrusted data.
- Capability inventory: The skill has access to shell commands via
Bash(firecrawl *)andBash(npx firecrawl *). - Sanitization: No specific sanitization or content filtering is mentioned for the retrieved markdown passages.
- [COMMAND_EXECUTION]: The skill utilizes the
firecrawlCLI andnpx firecrawlcommands for searching and storing results in the local.firecrawl/directory. These are vendor-specific tools used for the skill's primary developer search functionality. - [EXTERNAL_DOWNLOADS]: The skill uses
npx firecrawl, which allows the agent to download and run thefirecrawlpackage from the NPM registry. This is a standard mechanism for utilizing the vendor's CLI tool.
Audit Metadata