update-config

72 / 100 · Review before installing

Check before installing. Some of what it can do is expected: a coding skill usually runs build and test commands.

By asgeirtj/system_prompts_leaks (GitHub) · coding · 71,387 stars · scanned at commit 2209631

Use this skill to configure the Claude Code harness via settings.json. Automated behaviors ("from now on when X", "each time X", "whenever X", "before/after X") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions ("allow X", "add permission", "move permission to"), env vars ("set X=Y"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: "allow npm commands…

Works with any agent that supports SKILL.md skills.

What this skill can do

Changes files outside its own folder

The author does not mention this.

Found in 1 place.

Anthropic/claude-code/skills/update-config/SKILL.md, line 299"command": "jq -r '.tool_input.command' >> ~/.claude/bash-log.txt"

Runs commands on your computer

This is disclosed by the author in the skill's SKILL.md or README. Expected for a coding skill.

Found in 1 place.

Anthropic/claude-code/skills/update-config/SKILL.md, line 311echo '{"systemMessage": "Session complete!"}'

Connects to the internet

The author does not mention this.

Found in 11 places.

Anthropic/claude-code/skills/update-config/SKILL.md, line 1710"description": "Version or range to fetch (e.g. "1.4.0", "^1.4"); defaults to the latest dist-tag",
Anthropic/claude-code/skills/update-config/SKILL.md, line 2264"description": "Version or range to fetch (e.g. "1.4.0", "^1.4"); defaults to the latest dist-tag",
Anthropic/claude-code/skills/update-config/SKILL.md, line 2811"description": "Version or range to fetch (e.g. "1.4.0", "^1.4"); defaults to the latest dist-tag",

Show 8 more

Anthropic/claude-code/skills/update-config/SKILL.md, line 3331"description": "Version or range to fetch (e.g. "1.4.0", "^1.4"); defaults to the latest dist-tag",
Anthropic/claude-code/skills/update-config/SKILL.md, line 3851"description": "Version or range to fetch (e.g. "1.4.0", "^1.4"); defaults to the latest dist-tag",
Anthropic/claude-code/skills/update-config/SKILL.md, line 4350"description": "Skip the WebFetch blocklist check for enterprise environments with restrictive security policies",
Anthropic/claude-code/skills/update-config/SKILL.md, line 4375"description": "Domains sandboxed commands may reach without a prompt (wildcards such as *.example.com supported). Merged with WebFetch(domain:…) allow rules an
Anthropic/claude-code/skills/update-config/SKILL.md, line 4389"description": "When true, the sandbox runtime deterministically denies hosts not in allowedDomains instead of prompting. Enforced for sandboxed commands only —
Anthropic/claude-code/skills/update-config/SKILL.md, line 4393"description": "When true (and set in managed settings), only allowedDomains and WebFetch(domain:...) allow rules from managed settings are respected. User, pro
Anthropic/claude-code/skills/update-config/SKILL.md, line 4419"description": "Local TCP port of your own HTTP proxy for sandboxed traffic, used instead of the proxy Claude Code runs. When managed settings or a --settings f
Anthropic/claude-code/skills/update-config/SKILL.md, line 4423"description": "Local TCP port of your own SOCKS5 proxy for sandboxed traffic, used instead of the proxy Claude Code runs. When managed settings or a --settings

Reads your saved credentials, such as SSH keys or .env files

This is disclosed by the author in the skill's SKILL.md or README.

Found in 2 places.

Anthropic/claude-code/skills/update-config/SKILL.md, line 4308"description": "Managed settings only (managed-settings.json, MDM, or server-managed). The API providers Claude Code may use on this machine: "anthropic" (the A
Anthropic/claude-code/skills/update-config/SKILL.md, line 5237"description": "SSH host in format "user@hostname" or "hostname", or a host alias from ~/.ssh/config",

Safer alternatives

Low-risk skills in the same category (coding) that look related. Check that one does what you need.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'update-config' ] || [ -L ~/.agents/skills/'update-config' ]; then echo 'A skill folder named update-config already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/asgeirtj/system_prompts_leaks' "$d" && git -C "$d" checkout --quiet '2209631d6d3da737c22159ed03c5127734b187f3' -- 'Anthropic/claude-code/skills/update-config' && mkdir -p ~/.agents/skills && cp -R "$d"/'Anthropic/claude-code/skills/update-config' ~/.agents/skills/'update-config' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'update-config' ~/.claude/skills/'update-config' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for asgeirtj/system_prompts_leaks shows the score of its lowest-scoring skill.

SkillTrust badge for asgeirtj/system_prompts_leaks

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/asgeirtj/system_prompts_leaks.svg)](https://zalavijaysinh.github.io/skilltrust/repos/asgeirtj/system_prompts_leaks/)

Score history

Date	Version	Score
2026-11-14	`2209631`	72
2026-11-10	`fc0108f`	72