hreng-skills
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a bash script and a python script to validate JSON and Markdown templates. These scripts are safe and operate only on local files.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to processing team and roadmap data.
- Ingestion points: Data from team rosters and roadmap descriptions.
- Boundary markers: No delimiters are used in templates to separate data from instructions.
- Capability inventory: Limited to file generation; no network or system access.
- Sanitization: No input validation or escaping for injection strings is present.
- [EXTERNAL_DOWNLOADS]: The skill references a JSON schema on a vendor-related domain for data structure validation.
Audit Metadata