speckit-tasks
Fail
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: HIGHCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local bash script located at
.specify/scripts/bash/setup-tasks.sh. This enables the execution of code present in the project being analyzed.\n- [DYNAMIC_EXECUTION]: The skill features a dynamic extension hook system that reads command names from a local configuration file (.specify/extensions.yml) and instructs the agent to execute them usingEXECUTE_COMMAND. This allows project-level configuration to trigger arbitrary command execution within the agent session.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from multiple project files without adequate boundary markers or sanitization, which then influences its command execution logic.\n - Ingestion points:
.specify/extensions.yml,plan.md,spec.md,data-model.md,contracts/,research.md,quickstart.md, and.specify/memory/constitution.md.\n - Boundary markers: None identified.\n
- Capability inventory: Execution of extension hooks (
EXECUTE_COMMAND) and a setup bash script.\n - Sanitization: None identified; raw input from these files is used to construct commands and drive the task generation process.
Recommendations
- AI detected serious security threats
Audit Metadata