SKILLEMALL.ai
GitHub ↗ RU Sign in

CC VibeSec-Skill

This skill helps Claude write secure web applications. Use this when working on any web application or when a user requests a scan or audit to ensure security best practices are followed.

BehiSecc/VibeSec-Skill Agent Skills author: BehiSecc 3 files body ≈ 6 129 tokens Open the sourcegithub.com↗ analyzed 5 d ago

This skill helps Claude write secure web applications.

As a process C 60/100 · Has gaps — weak spots: result and completion, running it twice

GeneratorWordExcelSecuritySoftware developmenttype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
83/100
safety, quality, tests
Safety 60%
91
Quality 40%
70
Run on models
none yet
Process rating
C
60/100
Has gaps
Result and completion w 14
0
Running it twice w 4
30
Failures and branches w 10
50
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 5

✓ No critical or high findings

Medium and low: 5
  • medium Obfuscation uni-mixed-script-word SKILL.md:292
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (1 occurrence)
    | Unicode normalization | `https://legіt.com` (Cyrillic і) | IDN homograph attack |
  • low Risky intent intent-offensive-security README.md:5
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    An AI skill that brings 5+ years of bug bounty hunting experience directly into your AI coding workflow - so LLM models write secure code from the start.
  • low Risky intent intent-offensive-security README.md:84
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | **Access Control** | IDOR, Privilege Escalation, Horizontal/Vertical Access, Mass Assignment, Token Revocation |
  • low Risky intent intent-offensive-security SKILL.md:54
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **Privilege Escalation**: Validate role changes server-side; never trust role info from client
  • low Risky intent intent-offensive-security SKILL.md:709
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Accepting unfiltered request bodies can lead to privilege escalation.

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning body-long SKILL.md body ≈ 6129 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 191): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 60/100

  • 0Result and completion. Does not say what the result is
  • 30Running it twice. 6 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 60Steps. 245 steps, 6 vague phrases
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 6129 tokens
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +3Description length 187: enough signal without eating the budget
  • +4Structure: 61 headings
  • +3Step-by-step instructions: 245 items
  • +4Has examples (17 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.