speckit-checklist
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a repository-local PowerShell script located at
.specify/scripts/powershell/check-prerequisites.ps1to parse project metadata and templates. It includes logic to escape user arguments to prevent command injection. - [DYNAMIC_EXECUTION]: The skill implements an extension hook mechanism that reads command strings from a local configuration file (
.specify/extensions.yml). Mandatory hooks are automatically invoked by the agent, allowing local project configuration to drive agent behavior. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes external project data. Ingestion points: Reads
$ARGUMENTS,spec.md,plan.md,tasks.md, and.specify/extensions.yml. Boundary markers: None present; content is processed without explicit delimiters. Capability inventory: Shell execution (hooks/prerequisites), file read/write. Sanitization: Basic shell argument escaping is instructed for the prerequisites call. Remediation: Wrap project file content in unique delimiters and provide explicit instructions to the agent to treat the enclosed text as data rather than instructions.
Audit Metadata