speckit-analyze
Warn
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script located at
.specify/scripts/bash/check-prerequisites.shduring the initialization phase.- [COMMAND_EXECUTION]: The skill implements an extension hook system that parses.specify/extensions.ymland instructs the agent to execute any commands defined within that file using theEXECUTE_COMMANDdirective. This allows project-level configuration to dictate arbitrary shell operations.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and acting upon untrusted data from the project's configuration files. - Ingestion points: The agent reads and interprets content from
.specify/extensions.yml. - Boundary markers: No boundary markers or 'ignore' instructions are provided to the agent to prevent malicious commands in the configuration from being executed.
- Capability inventory: The agent has the capability to execute shell commands and run local scripts.
- Sanitization: There is no validation or sanitization of the command strings retrieved from the extension file before they are passed to the execution environment.
Audit Metadata