5skill

Create and manage Product Requirements Documents with user stories, verifiable acceptance criteria, and ordered implementation tasks.

This skill's PRD templates and guidance are generally useful for planning, but the runtime documentation contains risky operational instructions. Before using it: (1) Do NOT run the provided 'unattended agentic loop' as-is — it can autonomously modify your repo and run indefinitely. (2) Never use the '--dangerously-skip-permissions' flag or other directives that bypass agent safety checks. (3) Run any agentic execution in an isolated sandbox or throwaway clone, with human review steps enabled. (4) Verify and restrict any CLIs or tokens the agent would need (claude, opencode, git, jq, dev-browser) and add those requirements to the skill metadata. (5) Consider adding explicit human-in-the-loop approval before commits, and back up your repository before testing. If you need the automation, require the skill to declare required binaries/credentials and remove instructions that bypass permissions.

Type: OpenClaw Skill Name: prd-skill2026030303 Version: 1.0.0 The skill bundle defines a framework for managing Product Requirements Documents (PRDs) designed for autonomous AI agents. It is classified as suspicious because the documentation in 'references/agent-usage.md' explicitly encourages users to run AI agents using high-risk configurations, specifically recommending the '--dangerously-skip-permissions' flag with Claude Code. This configuration bypasses all security prompts, creating a significant risk of arbitrary command execution if an agent processes a malicious task within the 'prd.json' file. While the skill itself manages data, it promotes an unsafe execution environment without sufficient warnings.