Skill Manager

    2

    Secure manager for skills featuring whitelisted GitHub/npm installation and AST-based security auditing.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    skill-manager

    Example session with this skill installed

    Install the meeting-notes skill from GitHub into my local ~/.dsh/skills library, run a static security audit on it, and report the audit level with any high/critical findings before I use it. Show the install source, the audit result, and the recommended next checks.

    • Read your context and instructions
    • Compiled the -manager

    Summary

    Installed the meeting-notes skill from a whitelisted GitHub source into ~/.dsh/skills/meeting-notes and ran a read-only static audit. Sample result: level safe, count: 0 findings. This is a heuristic rule-based check: it means no rule fired in this sample, not a certification that the skill has no vulnerabilities.

    Installation Record

    StepDetailStatus
    Sourcegithub:owner/meeting-notes; host allowlist (codeload.github.com)Accepted
    NetworkHTTP 3xx redirects not followed; non-allowlisted/internal hosts blockedOK
    ExtractionEntry-count and size budgets; tar-slip path-boundary validationOK
    PlacementExtracted to ~/.dsh/skills/meeting-notes; existing directory not overwrittenOK

    Audit Output

    Command: python scripts/dsh_tools.py audit meeting-notes --json

    {
      "name": "meeting-notes",
      "level": "safe",
      "count": 0,
      "fail": false,
      "fail_on": "",
      "findings": []
    }
    

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Managing third-party AI agent skills is a security minefield of prompt injections, credential theft, and unauthorized script execution. This package provides a secure infrastructure to discover, install, and audit DeepSeek Harness (DSH) compatible skills. It enforces strict domain whitelisting for downloads and implements 12 distinct security audit rules, including AST-based Python analysis, to prevent data exfiltration and shell-pipe attacks before a single line of text is loaded into your agent's context.

    What it does

    • Secure installation downloads SKILL.md packages from whitelisted GitHub and npm sources with SSRF protection.
    • Static security auditing detects prompt injection, credential phishing, and dangerous shell commands using AST and pattern matching.
    • Skill discovery lists all locally installed capabilities with their specific triggers and metadata.
    • Plugin identification distinguishes between pure Markdown-based skills and TypeScript-based DSH function plugins.
    • Safe loading provides a read-only preview of skill instructions without executing them, preventing unauthorized invocations.

    How it works

    1. Locate existing skills or identify new local directories using the list and info commands.
    2. Install remote skills via github:owner/repo or npm:package identifiers with built-in tar-bomb protection.
    3. Audit the package using audit to check for high-risk findings like rm -rf or network exfiltration patterns.
    4. Load the audited content into the agent context for task execution.

    Frameworks & tools

    Built for the DeepSeek Harness (DSH) ecosystem. Requires Python 3.9 or higher (standard library only). Works with any LLM agent capable of reading Markdown files and frontmatter.

    Why this beats prompting it yourself

    Manual auditing of complex agent instructions is prone to human error and ignores hidden malicious scripts. This tool automates the detection of exfiltration patterns and dangerous shell commands that simple system prompts cannot reliably catch.

    Use cases

    • Auditing a third-party GitHub repository for hidden prompt injections or credential-stealing instructions.
    • Centralizing a library of custom agent skills in a standard local directory (~/.dsh/skills).
    • Safely downloading and extracting SKILL.md files from npm without manual zip handling.
    • Verifying if a local directory is a function-based plugin or a text-based skill.

    Known limitations

    Static auditing is heuristic and may have false positives or negatives. Binary files and files over 1MB are skipped during security scans.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Auditing is heuristic and may miss sophisticated obfuscated attacks. Skips binary files and files >1MB. Requires Python 3.9+ for full AST-based security checks.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 6 days ago

    • Free with an Agensi account

    Accounts
    GitHubEvilExample
    Software
    Python

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Environment Variables

    Allowed Hosts

    evil.example
    api.example.com
    github.com
    registry.npmjs.org
    codeload.github.com
    example.com
    evil.example.com
    evil
    e
    backup.example.example
    files.example.com
    ci.example.com
    evil.example.
    Listed8 days ago
    Updated6 days ago

    What's inside

    Frequently Asked Questions

    The manager uses Abstract Syntax Tree (AST) analysis to scan for dangerous patterns like shell injections, data exfiltration scripts, and prompt-based credential phishing before any code or instruction is loaded into your agent.

    It is specifically designed for the DeepSeek Harness (DSH) ecosystem and works with any LLM agent that can interpret Markdown files and frontmatter, provided you are running Python 3.9+.

    No, the tool enforces a strict domain whitelist for GitHub and npm sources, including SSRF and tar-bomb protection to ensure remote packages are safe to download.

    The 'list' and 'info' commands allow you to centralize your library in a standard directory, automatically distinguishing between text-based SKILL.md files and complex TypeScript-based function plugins.

    While highly effective at catching known patterns, the audit is heuristic-based; it skips files over 1MB and binary data, so manual oversight is still recommended for exceptionally large assets.

    New in Agents & Orchestration

    Free