harness-engineering
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The scaffolding script and generated hook scripts (
context-injector.py) utilizesubprocess.check_outputto executegitcommands for branch and commit history discovery. - [PROMPT_INJECTION]: The framework implements an automated context injection mechanism (Category 8) vulnerable to indirect prompt injection. • Ingestion points: Reads content from
docs/specs/,docs/contracts/, andfeature_list.json. • Boundary markers: Injects data using simple text headers like "Project context:" without strong delimiters or instructions to ignore nested directives. • Capability inventory: The framework explicitly permits extensive agent capabilities including file editing and shell execution. • Sanitization: External file content is interpolated directly into the prompt without escaping or validation. - [DYNAMIC_EXECUTION]: The scaffolding script uses
__import__to dynamically load thedatetimemodule for date substitution in templates.
Audit Metadata