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.sh during the initialization phase.- [COMMAND_EXECUTION]: The skill implements an extension hook system that parses .specify/extensions.yml and instructs the agent to execute any commands defined within that file using the EXECUTE_COMMAND directive. 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
Risk Level
MEDIUM
Analyzed
Aug 7, 2026, 06:22 AM
Security Audit — agent-trust-hub — speckit-analyze