speckit-plan
Fail
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: HIGHCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to automatically execute shell commands found in the
.specify/extensions.ymlfile located in the project root. Evidence inSKILL.md: 'For each executable hook, output the following... EXECUTE_COMMAND: {command}... you MUST actually invoke the hook and wait for it to finish.' - [DYNAMIC_EXECUTION]: The skill executes a local script as part of its setup phase. Evidence in
SKILL.md: '1. Setup: Run{SCRIPT}from repo root'. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from project-controlled files and uses it to drive tool execution. Ingestion points:
.specify/extensions.ymlandFEATURE_SPECinSKILL.md. Boundary markers: None identified. Capability inventory: Arbitrary shell command execution. Sanitization: No sanitization or validation of command strings is performed before execution. - [EXTERNAL_DOWNLOADS]: The skill references the official GitHub Spec Kit repository as the source for its planning and implementation templates.
Recommendations
- AI detected serious security threats
Audit Metadata