sonar-fix-issue
Fail
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is vulnerable to command injection in Step 2 when executing CLI commands. The instruction
sonar api get "/api/rules/show?key=<rule-key>"interpolates the user-controlled<rule-key>argument directly into a shell command string. An attacker could provide a malicious string containing shell metacharacters (e.g.,;,&,|,`) to execute unauthorized code on the host system. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it processes external rule data.
- Ingestion points: The agent fetches rule descriptions and remediation guidance from the SonarQube API or MCP tool as described in
SKILL.md. - Boundary markers: The skill does not implement delimiters or instructions to treat the fetched content as untrusted or to ignore embedded instructions.
- Capability inventory: The skill leverages
Read,Edit, andBashtools, which could be misused if the agent inadvertently executes instructions contained within fetched rule descriptions. - Sanitization: There is no evidence of validation or filtering performed on the rule content before it is presented to the agent for remediation tasks.
Recommendations
- AI detected serious security threats
Audit Metadata