sonar-sweep-cli

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes several triage and mutation commands such as pr-report, pr-coverage, pr-review, and issue-accept using the npx runner.
  • [EXTERNAL_DOWNLOADS]: The skill triggers the download of the sonar-sweep package from the NPM registry at runtime via the npx command.
  • [REMOTE_CODE_EXECUTION]: The skill dynamically downloads and executes code from the NPM registry using the npx sonar-sweep pattern, which is an external source.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it processes untrusted data from SonarQube Cloud reports.
  • Ingestion points: Data enters the assistant context via the output of pr-report, pr-issues, and pr-review commands defined in SKILL.md.
  • Boundary markers: There are no explicit delimiters or specific instructions to ignore embedded directives in the ingested SonarQube data.
  • Capability inventory: The skill allows for shell command execution and mutation of external project state via issue-accept.
  • Sanitization: No evidence of sanitization or filtering is provided for the content received from the SonarQube API.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 01:45 PM