speckit-implement

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local prerequisite script (.specify/scripts/bash/check-prerequisites.sh) and repository verification commands (git rev-parse) to ensure the environment is ready for implementation.
  • [PROMPT_INJECTION]: The skill identifies a potential indirect prompt injection surface as it consumes and acts on instructions from markdown files. (1) Ingestion points: specs//tasks.md, plan.md, and files in the checklists directory. (2) Boundary markers: No specific delimiters or safety warnings are included for these data sources. (3) Capability inventory: The skill can execute shell scripts and perform arbitrary file writes. (4) Sanitization: The skill does not describe a process for validating the content of the tasks before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:11 PM
Security Audit — agent-trust-hub — speckit-implement