writing-skills
Verdict safe, but 2 findings (1 medium, 1 low), mainly policy violation, skill discovery abuse. Most recent scan 2026-02-08.
Second scanner: NVIDIA SkillSpector
The two scanners disagree: Cisco found nothing and SkillSpector says do not install. One of them has a blind spot here; read the skill before trusting either. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Use when creating new skills, editing existing skills, or verifying skills work before deployment
- Package
- 7 files, 101 KB
- SKILL.md
- 3185 words, 12+ sections
- Code
- JavaScript (1)
SKILL.md covers: Writing Skills · Overview · What is a Skill? · TDD Mapping for Skills · When to Create a Skill · Skill Types · Technique · Pattern · Reference · Directory Structure · SKILL.md Structure · Skill Name
Findings
MEDIUM SKILL DISCOVERY ABUSE detected by YARA Skill Discovery Abusestatic
Detects manipulation of skill discovery to increase unwanted activation: official skill
SKILL.md:15
**Official guidance:** For Anthropic's official skill authoring best practices, see anthropic-best-practices.md. This document provides additional patterns and guidelines that complement the TDD-focused approach in this skill.LOW Skill does not specify a license Policy Violationstatic
Skill manifest does not include a 'license' field. Specifying a license helps users understand usage terms.
SKILL.md
What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 22 KB |
anthropic-best-practices.md | doc | 45 KB |
graphviz-conventions.dot | other | 5.8 KB |
persuasion-principles.md | doc | 5.8 KB |
render-graphs.js | script | 4.7 KB |
testing-skills-with-subagents.md | doc | 12 KB |
examples/CLAUDE_MD_TESTING.md | doc | 5.3 KB |
External hosts referenced
mintcdn.com platform.claude.com
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Package contents recorded 2026-10-22 at commit 06b92f36820f. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://github.com/obra/superpowers
- Raw scan result: writing-skills-scan.json
- Badge for your README:
- Request a re-scan