agentsclimarketplace

Security hygiene

Skill Tibsfox/gsd-skill-creator/examples/skills/workflow/security-hygiene

Introduces a comprehensive agent-based framework for guided software development (GSD)

Install
npx -y skills add Tibsfox/gsd-skill-creator --skill security-hygiene

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

What its author says it does

Copied from the file, not written here

Security hygiene for GSD's self-modifying skill and agent system. Use this skill whenever: creating, editing, or deleting skill files (.claude/skills/, .claude/commands/), modifying agent definitions (.claude/agents/), working with YAML configuration or chipset files, handling JSONL observation data (.planning/patterns/), processing community-contributed skills or chipsets, any file path operations that could involve user input, or when installing/updating project-claude configuration. Also activates for discussions about skill-creator security, trust models, or content hygiene.

SKILL.md

2.8 KB, 419 tokens by cl100k_base, as published. Nobody here has run it

Security Hygiene

Security Philosophy

This is a self-modifying system. Security should work like a helpful companion, not an adversarial checkpoint — zen and the art of programming. Tools protect by default, guide by suggestion, block only when there is a real reason.

Threat Surface

VectorRiskCheck
Path traversalSkill names used in file paths could escape directorySanitize all skill names: alphanumeric, hyphens, underscores only. Reject .., /, \.
YAML deserializationUnsafe YAML loading executes arbitrary codeUse safe parsing only (yaml.safe_load or equivalent). Never yaml.load with untrusted input.
Data poisoningAppend-only JSONL could contain injected entriesValidate entries on read: check schema, reject oversized entries, verify timestamps are monotonic.
Permission bypassAutomated workflows might skip user confirmationNever bypass user confirmation for skill application, even in YOLO mode. YOLO applies to GSD workflow commands, not skill modifications.
Cross-project leakageUser-level skills might expose project-specific patternsUser-level skills must be generic. Project-specific patterns stay in project-level skills.
Observation privacyPattern data could leak into shared repos.planning/patterns/ must be in .gitignore. Verify on any git operation.

Content Hygiene Rules

When processing community-contributed content (skills, chipsets, LoRA adapters):

  • Check for embedded commands or script execution
  • Verify YAML does not contain unsafe tags (!!python/object, etc.)
  • Validate that skill descriptions match their actual content
  • Quarantine new community content for review before activation

The Staging Layer Principle

"The user's ability to work should be reasonable. Security should also be reasonable. We strive for the clean intersection." Do not over-alert. Do not create friction for normal operations. Surface findings only when something genuinely warrants attention.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.