SKILLEMALL.ai
GitHub ↗ RU Sign in

AC input-guard

Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.

modbender/skill-library-mcp Agent Skills author: modbender MIT 14 files · 2 scripts body ≈ 3 579 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks.

As a process C 59/100 · Has gaps — weak spots: when it triggers, failures and branches, running it twice

IntegrationSlackAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
A
94/100
safety, quality, tests
Safety 60%
96
Quality 40%
90
Run on models
none yet
Process rating
C
59/100
Has gaps
Failures and branches w 10
0
When it triggers w 12
20
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 4

    ✓ No critical or high findings

    Medium and low: 4
    • low Exfiltration read-dotenv TESTING.md:32
      Reads a .env file (test fixture / example file; documentation of a security skill)
      cp .env.template .env
      fixturesecurity skill

    A further 3 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 59/100

    • 0Failures and branches. Linear process with no failure handling
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 6 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 85Steps. 63 steps, 2 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3579 tokens
    • 100Progress reporting. Reports progress
    • low 14 top-level sections: this looks like several domains in one skill

    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)
    • +1No license
    • +2Single-language instructions
    • +3Description length 221: enough signal without eating the budget
    • +4Structure: 35 headings
    • +3Step-by-step instructions: 63 items
    • +3Output format is stated explicitly
    • +4Has examples (13 code blocks)
    • +3All 5 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.