help-and-support
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- COMMAND_EXECUTION (LOW): The skill templates shell commands (fdx call ...) that incorporate raw user input from the --question, --title, and --description parameters. This creates a surface for command injection if an attacker includes shell metacharacters like semicolons or backticks to execute arbitrary commands.
- PROMPT_INJECTION (LOW): This skill contains an Indirect Prompt Injection surface as defined in Category 8. * Ingestion points: User-provided text for support questions and bug descriptions is ingested via the skill parameters. * Boundary markers: Absent; the bash command examples do not use delimiters or provide instructions to escape embedded content. * Capability inventory: The skill utilizes the Bash tool to execute fdx CLI commands on the system. * Sanitization: There is no sanitization or validation logic provided within the skill to filter or escape user-controlled strings before execution.
Audit Metadata