update-config

update-config is a Claude Code configuration skill for AI agents, published by asgeirtj in the system_prompts_leaks repository on GitHub. Skillspace rates update-config F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.

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", "add bq permission to global settings", "move permission to user settings", "set DEBUG=true", "when claude stops show X". For simple settings like theme/model, suggest the /config command.

Grade
F
Quality
45 / 100
Safety
Risky
GitHub stars
65,832

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since.

View source on GitHubasgeirtj/system_prompts_leaks

Our review

Architecture
69 / 100
Maturity
Basic: a single SKILL.md
Security scan
High-risk patterns
License
Not declared. Check the repository before reusing it.

What the scanner flagged

  • exfiltration language
  • references sensitive credential env
  • accesses sensitive system files
  • mentions secrets in text

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Claude Code configuration

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.