sonar-dependency-risks
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes vulnerability information (dependency names, risks, and CVEs) from external SonarQube API responses and tool outputs. This constitutes an untrusted data ingestion surface.
- Ingestion points: Results from the
mcp__sonarqube__search_dependency_riskstool and the output fromsonar api getorsonar analyze. - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to disregard potentially malicious commands embedded within the external vulnerability metadata.
- Capability inventory: The skill has the capability to read local files (e.g.,
sonar-project.properties) and execute shell commands via thesonarCLI and container runtimes. - Sanitization: No explicit sanitization or content validation is performed on the data retrieved from the SonarQube server before it is rendered to the user.
Audit Metadata