solo-pipeline
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to execute local launcher scripts such assolo-research.sh,solo-dev.sh, andsolo-dashboard.sh. These scripts are expected to be part of the vendor's installation package in the plugin root. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted user input and passes it to internal logic.
- Ingestion points: User arguments (idea name, project name, stack, features) are parsed from the
$ARGUMENTSvariable in Step 1. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the user-provided arguments when they are interpolated into the shell command strings.
- Capability inventory: The skill has access to
Bash(command execution),Read/Write(file system access to~/.soloand project directories), andAskUserQuestion. - Sanitization: There is no evidence of argument sanitization or validation to prevent shell injection or malicious command chaining within the provided instructions.
Audit Metadata