title-research

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the firecrawl CLI and a local Python script research.py using subprocess.run(). This is the intended functionality of the skill to perform its research task. The commands are constructed with defined arguments and do not take direct, unsanitized user input into the shell environment.
  • [EXTERNAL_DOWNLOADS]: The skill relies on the firecrawl CLI, which must be pre-installed and authenticated by the user. It does not perform arbitrary downloads from untrusted sources during runtime.
  • [REMOTE_CODE_EXECUTION]: No remote code execution patterns were detected. All execution is local to the provided scripts or the user-installed firecrawl tool.
  • [CREDENTIALS_UNSAFE]: No hardcoded credentials or sensitive environment variable leaks were found. The skill assumes the user has already authenticated the firecrawl CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 02:48 PM
Security Audit — agent-trust-hub — title-research