sonar
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources that are not fully controlled by the agent, such as GitHub PR details and SonarCloud API responses, which could contain malicious instructions.
- Ingestion points: Data is ingested via
gh pr view,gh pr checks, and SonarCloud search APIs for issues and hotspots (inSKILL.md). - Boundary markers: Absent; there are no defined delimiters or instructions to the agent to disregard instructions potentially embedded within the PR metadata or SonarCloud issue descriptions.
- Capability inventory: The skill executes
ghCLI commands and performs network operations usingctx_executeorcurl(inSKILL.md). - Sanitization: The instructions do not specify any validation, escaping, or filtering of the content retrieved from GitHub or SonarCloud before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill performs shell command execution using the GitHub CLI (
gh) and potentiallycurlto manage PR states and query job statuses. These operations are scoped to the intended functionality of integrating with development workflows.
Audit Metadata