status
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the bash command
parallel-cli research status "$ARGUMENTS" --json. The direct interpolation of the$ARGUMENTSvariable, which contains untrusted user input, into a shell command without escaping or validation constitutes a command injection surface. Maliciously crafted input containing shell metacharacters (e.g., backticks or subshells) could potentially lead to unauthorized command execution within the agent's environment. - [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface. 1. Ingestion points: The
$ARGUMENTSvariable inSKILL.mdcaptures user input. 2. Boundary markers: No markers or escaping mechanisms are used to wrap the input. 3. Capability inventory: The skill utilizes the Bash tool to execute system-level commands. 4. Sanitization: No sanitization or validation of the input is performed before it is passed to the command line tool.
Audit Metadata