sample-scaffolder
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes content from untrusted external skill submissions to populate documentation templates.
- Ingestion points: Skill submission and PR content (as described in the Step by Step Workflow).
- Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore instructions embedded in the submission data.
- Capability inventory: File system write access for creating README.md and modifying assets/sample.json.
- Sanitization: Absent; the skill does not include steps to sanitize or validate content before interpolating it into templates.
- [COMMAND_EXECUTION]: The skill involves local file system operations, including copying and renaming template files and generating new files based on submission data. These operations are standard for a scaffolding utility but are performed using data provided by the user/PR author.
Audit Metadata