speckit-analyze

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 shell script located at .specify/scripts/bash/check-prerequisites.sh during the initialization step.
  • [DYNAMIC_EXECUTION]: The skill parses .specify/extensions.yml and automatically triggers the execution of commands using the EXECUTE_COMMAND directive for any mandatory hooks defined in the file. This behavior allows the content of a configuration file in the repository to dictate which commands the agent runs.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from multiple external files including spec.md, plan.md, tasks.md, .specify/memory/constitution.md, and .specify/extensions.yml.
  • Ingestion points: Files spec.md, plan.md, tasks.md, constitution.md, and extensions.yml (SKILL.md).
  • Boundary markers: None identified; the skill directly loads and creates internal representations of these artifacts.
  • Capability inventory: Executes local scripts and triggers arbitrary slash commands via the hook system.
  • Sanitization: No evidence of sanitization or validation of the content parsed from the project artifacts.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 12, 2026, 03:23 PM