gsd

WarnAudited by ClawScan on May 10, 2026.

Overview

This is a coherent project-automation skill, but it can spawn autonomous agents, run shell commands, edit files, and make git changes, so it should be reviewed before use.

Use this only in a repository where you are comfortable with automated edits, shell commands, and git commits. Start on a separate branch, review diffs before accepting changes, consider disabling automatic planning-doc commits, and avoid placing secrets in GSD planning/debug context.

Findings (6)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

A debugging run could change project files or run local commands before the user has reviewed each specific change.

Why it was flagged

The debug workflow gives a spawned debugging agent shell and edit capabilities and frames its goal as finding and fixing, with a completion path where a fix has already been applied.

Skill content
allowed-tools: Read, Bash, Write, Edit ... <mode> goal: find_and_fix ... If `## DEBUG COMPLETE`: Display fix applied
Recommendation

Run this only in a clean branch or disposable workspace, and require explicit approval before any Bash/Edit action or before applying fixes.

What this means

Multiple agents may read, test, and write diagnostic artifacts at once, making it harder to predict or review the full set of actions.

Why it was flagged

The workflow intentionally launches multiple general-purpose subagents to investigate issues in parallel, which expands autonomous activity across the codebase.

Skill content
Spawning parallel debug agents ... Each agent will ... Investigate autonomously ... Task(... subagent_type="general-purpose" ...)
Recommendation

Limit the number of parallel agents, keep their tool access scoped, and require a user checkpoint before moving from diagnosis to planning or fixes.

What this means

The skill can alter repository history and planning files as part of normal use.

Why it was flagged

Milestone completion includes local deletion of a planning file and git commit/tag operations. These are scoped to the planning workflow but still mutate the repository.

Skill content
rm .planning/REQUIREMENTS.md ... git add .planning/ ... git commit -m "chore: archive v{version} milestone" ... git tag -a "v{version}"
Recommendation

Use a branch, review diffs before committing, and confirm that deleting .planning/REQUIREMENTS.md is acceptable for the project.

What this means

Unexpected phase arguments could cause the workflow to operate on the wrong planning directory or produce confusing shell behavior.

Why it was flagged

User-provided phase input is interpolated into Bash snippets without robust validation. This appears scoped to phase selection, but malformed input could select unintended files or phases.

Skill content
PADDED_PHASE=$(printf "%02d" ${PHASE} 2>/dev/null || echo "${PHASE}")
Recommendation

Validate phase arguments against a strict numeric/decimal pattern and quote variable expansions in shell snippets.

What this means

Private project details, pasted errors, or sensitive ideas may become stored in the repo if captured in planning docs.

Why it was flagged

The workflow persists conversation-derived context into .planning files and commits them by default when commit_docs is true.

Skill content
Capture idea or task as todo from current conversation context ... git commit -m "docs: capture todo - ${TITLE}"
Recommendation

Review .planning contents before committing, set commit_docs to false for sensitive projects, and avoid pasting secrets into GSD conversations.

What this means

The design workflow may fail or depend on an unreviewed local file if one exists at that absolute path.

Why it was flagged

The workflow references a design-specialist subagent prompt, but the provided manifest does not include agents/design-specialist.md, leaving that subagent behavior unavailable for review.

Skill content
@/usr/lib/node_modules/clawdbot/skills/gsd/agents/design-specialist.md
Recommendation

Package and review every referenced agent prompt, or remove the missing reference and keep subagent prompts within the supplied skill files.