speckit-checklist-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 processes external documentation files (spec.md, plan.md, tasks.md) which could contain malicious instructions designed to influence the agent's behavior. 1. Ingestion points: spec.md, plan.md, and tasks.md located in the FEATURE_DIR identified by the prerequisite script. 2. Boundary markers: The instructions lack explicit delimiters or instructions to ignore commands embedded within the processed documentation. 3. Capability inventory: The skill can write new files to the file system and execute shell scripts for environment checks. 4. Sanitization: There is no evidence of sanitization or filtering of document content before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill executes a PowerShell script (check-prerequisites.ps1) to locate the project root and identify available documentation. The script performs standard directory traversal and file existence checks, which are benign but represent a capability that could be misused if command injection were present.
Audit Metadata