autobuild
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes stack-specific quality gates (lint, test, typecheck) and generates a
commits.shscript which is marked as executable usingchmod +xinreferences/ORCHESTRATION.md. - [PROMPT_INJECTION]: The skill processes external implementation plans (
plan-path) which serve as untrusted input. Malicious instructions or code within these plans could influence sub-agent behavior or lead to unintended command execution. - Ingestion points: The required
<plan-path>document specified inSKILL.md. - Boundary markers: Lacking explicit guards against instructions embedded in the plan document itself within the sub-agent prompts in
references/SUBAGENT-PROMPTS.md. - Capability inventory: Includes shell execution (
Bash), file writing, and sub-agent creation across all reference files. - Sanitization: Relies on the TDD micro-structure but does not sanitize the natural language content of the plan or the interpolated variables.
Audit Metadata