generate
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection. 1. Ingestion points: The $ARGUMENTS parameter in the SKILL.md file allows user-provided input to influence the command executed. 2. Boundary markers: No delimiters or safety instructions are provided to separate user input from the command logic. 3. Capability inventory: The skill allows execution of Bash(melos *) and Bash(flutter pub run *) via the Bash tool. 4. Sanitization: There is no evidence of input validation or escaping for the $ARGUMENTS string before it is passed to the shell.
- [COMMAND_EXECUTION]: The allowed-tools section uses the wildcard pattern melos *. This configuration allows for the execution of any arbitrary subcommand or flag supported by the Melos CLI, which is broader than the specific generation commands listed in the documentation.
Audit Metadata