speckit-implement

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a project-local shell script located at .specify/scripts/bash/check-prerequisites.sh to verify the environment state and extract project metadata.
  • [COMMAND_EXECUTION]: The skill dynamically constructs and executes slash commands (e.g., /speckit-git-commit) based on lifecycle hooks defined in the project's .specify/extensions.yml file.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core execution logic, including which commands are run and what tasks are performed, is derived from untrusted files in the project root. * Ingestion points: Reads implementation instructions and execution hooks from tasks.md, plan.md, and .specify/extensions.yml. * Boundary markers: No explicit isolation markers are used to separate external file content from system instructions. * Capability inventory: The skill has the ability to execute shell scripts and trigger secondary commands via the EXECUTE_COMMAND interface. * Sanitization: The skill does not validate or sanitize the content of the project configuration files before using them to drive agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 09:10 PM
Security Audit — agent-trust-hub — speckit-implement