deepsource

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the local deepsource CLI to interact with the vendor's platform. Commands like deepsource issues and deepsource report-card are used to fetch structured data for analysis. These operations are restricted to the tool's intended functionality.
  • [EXTERNAL_DOWNLOADS]: No unauthorized downloads or remote code execution patterns were detected. The skill references official vendor documentation and relies on the deepsource CLI, which is a legitimate tool provided by the vendor (DeepSourceCorp).
  • [SAFE]: No malicious patterns, such as hardcoded credentials, data exfiltration, or prompt injection, were found in the skill's instructions or the supporting shell script. The script scripts/check_auth.sh performs standard authentication and installation checks using safe practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 02:48 PM