speckit-checklist
Warn
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local bash script at
.specify/scripts/bash/check-prerequisites.shfrom the repository root to determine project parameters. - [COMMAND_EXECUTION]: The skill identifies and triggers the execution of additional agent commands (hooks) defined in the
.specify/extensions.ymlfile using theEXECUTE_COMMANDdirective. - [DYNAMIC_EXECUTION]: The skill dynamically determines which commands to run by parsing user-provided or project-provided configuration files (
extensions.yml), leading to variable execution paths based on local data. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from multiple project files and user arguments, which are then used to generate output and trigger system actions.
- Ingestion points: Reads project configuration from
.specify/extensions.ymland requirement documentation fromspec.md,plan.md, andtasks.md. - Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the content retrieved from these external files.
- Capability inventory: The skill has the ability to execute shell scripts, trigger subsequent agent commands, and create or append to files in the local file system.
- Sanitization: There is no evidence of sanitization, validation, or escaping of the content ingested from the project files before it is used to influence the checklist generation or hook execution.
Audit Metadata