speckit-tasks-zh
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill parses content from various project files such as spec.md and plan.md to generate task lists, creating an attack surface for indirect prompt injection. 1. Ingestion points: Reads multiple markdown files from the project's FEATURE_DIR. 2. Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or isolate instructions that may be embedded within the source documents. 3. Capability inventory: The skill has the ability to read files, execute local scripts, and write new markdown files. 4. Sanitization: The instructions do not specify any validation or sanitization of the content extracted from the design documents before it is processed.
- [COMMAND_EXECUTION]: The skill is configured to run local prerequisite check scripts (.specify/scripts/bash/check-prerequisites.sh and .specify/scripts/powershell/check-prerequisites.ps1). While the logic in the provided PowerShell script is benign (verifying git status and directory structure), the execution of scripts within the local environment is a sensitive capability that should be monitored for changes in the script source.
Audit Metadata