cmd-productionize
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill's primary workflow involves the systematic analysis of external application codebases, which presents an attack surface for indirect prompt injection where malicious instructions embedded in project files could influence agent behavior.
- Ingestion points: Project files including package.json, pubspec.yaml, requirements.txt, README files, and source code are analyzed in the 'Codebase Analysis Phase'.
- Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore embedded instructions when reading these external files.
- Capability inventory: The skill uses tools like 'TodoWrite' and is directed to implement code improvements, configuration changes, and deployment scripts, indicating write and execute capabilities.
- Sanitization: There is no mention of sanitizing or validating the content of the files processed during the audit phase.
Audit Metadata