specs-kit-code-cleanup

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions require the agent to search for and execute scripts defined in project configuration files such as package.json, Maven/Gradle plugins, composer scripts, and pyproject.toml. If a repository contains a malicious configuration file, the agent will execute those scripts in the local environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from project task files (TASK-XXX.md) and the source code itself to determine which files to modify and what technical debt to remove. It lacks explicit boundary markers or sanitization for this content.
  • Ingestion points: docs/specs/[id]/tasks/TASK-XXX.md, project source files, and configuration files (package.json, pyproject.toml, etc.).
  • Boundary markers: None identified in the instruction set for handling external data.
  • Capability inventory: File reading, file writing (cleanup), and shell command execution (linting, formatting, testing).
  • Sanitization: No evidence of input validation or command sanitization before executing project-defined tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:43 PM
Security Audit — agent-trust-hub — specs-kit-code-cleanup