Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Spectre SkillGuard

    1

    Scan AI agent skills before installing or using them.

    $15

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Spectre SkillGuard

    Spectre SkillGuard

    Example session with this skill installed

    Scan the skill folder at ./tools/github-optimizer and tell me if it is safe to use.

    • Read your context and instructions
    • Compiled the spectre skillguard

    I have completed the security audit of the github-optimizer skill located at ./tools/github-optimizer. The scan included a pattern pass for injection risks and a manual review of all command logic.

    Security Report: github-optimizer

    Verdict: ⚠️ Review before installing
    Security Score: 69/100

    Inventory Summary

    • Entry Point: SKILL.md (4.2 KB)
    • Scripts: src/main.py, scripts/setup.sh
    • MCP Config: None detected
    • Not checked: bin/helper.exe (Binary file, skipped)

    Findings

    IDSeverityLocationDescription
    P2.5Highsrc/main.py:42os.system call uses unvalidated user input, leading to potential shell injection.
    C3MediumSKILL.md:12Skill requests gh auth but logic in main.py attempts to read ~/.ssh/id_rsa.
    P4.1Lowscripts/setup.sh:5Hardcoded URL http://temp-binaries.xyz/dl found in download script.
    P1.2InfoSKILL.md:88Instructions contain "ignore previous instructions" as a test case string.

    Verification of High Severity Finding

    src/main.py:42: os.system("git commit -m " + user_input_msg)
    Risk: An attacker could provide a message like "; rm -rf /; #" to execute arbitrary commands.

    Next steps

    1. Sanitize the input in src/main.py using subprocess.run with an argument list instead of os.system.
    2. Remove the unauthorized access attempt to the SSH directory.
    3. Replace the unverified HTTP download link with a pinned hash or official source.

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

    About this skill

    AI agent skills and MCP servers run with your full system permissions, creating a massive attack surface for prompt injection and data exfiltration. Spectre SkillGuard is a read-only security auditor that scans untrusted skills and plugins to determine if they are safe to install. It treats all target files as untrusted data, ensuring that malicious instructions within the code cannot hijack the auditing process itself.

    What it does

    • Multi-vector Scanning identifies prompt injection, secret exposure, dangerous shell execution, and supply-chain risks.
    • Contextual Review analyzes whether a skill's promised behavior matches its actual internal logic and command execution.
    • Static Pattern Analysis runs a specialized scanner to detect known malicious patterns, hidden files, and suspicious network calls.
    • Risk Scoring calculates a 0-100 security score based on finding severity to provide a clear install/no-install verdict.
    • Isolation Auditing detects symlink attacks and persistence mechanisms designed to break out of restricted environments.

    How it works

    1. Target Selection provides a folder path, GitHub URL, or .mcp.json file for the agent to analyze.
    2. Inventory & Pattern Pass performs a file-level inventory and executes a read-only pattern scan to flag immediate red flags.
    3. Manual Verification re-opens every cited finding to quote the exact line of code and map it to a specific security rule.
    4. Final Reporting delivers a structured security verdict (OK, Review, or Do Not Install) with a score and a list of specific findings.

    Frameworks & tools

    The skill uses Git for remote cloning, Perl for pattern scanning, and standard Unix-style file inspection tools. It analyzes SKILL.md files, MCP configurations, and scripts written in Bash, Python, JavaScript, and TypeScript.

    Why this beats prompting it yourself

    Generic prompts often fall victim to the very injections they are supposed to detect, as the agent may follow instructions found inside the malicious file. This skill enforces a strict read-only execution policy and a standardized scoring rubric that prevents the auditor from being compromised by the target code.

    Use cases

    • Third-party Auditing before installing a community-made Claude plugin or MCP server.
    • CI/CD Safety Checks to scan changed skill files in a repository before merging them into a production agent.
    • Secret Detection to ensure internal API tokens or SSH keys aren't accidentally bundled in a skill's supporting files.
    • Functionality Verification to ensure a skill isn't making unauthorized curl requests to external domains.

    Known limitations

    Does not perform dynamic analysis or runtime monitoring of active agents. Requires Perl and Git to be available on the host system for full automated scanning and remote repo retrieval.

    Requires Perl for automated pattern scanning. Does not perform dynamic sandbox execution. Cannot scan binary-only skills without source code.

    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 any payment.

    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

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 12 days ago

    Requires

    Python
    Git

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Environment Variables
    Listed12 days ago

    What's inside

    Frequently Asked Questions

    Spectre SkillGuard acts as a specialized firewall for your AI environment, scanning third-party skills and MCP servers for hidden prompt injections, hardcoded API secrets, and unauthorized shell commands before you grant them system permissions.

    The skill is designed to analyze scripts and configuration files for Claude Desktop, MCP servers, and generic AI plugins written in Python, JavaScript, TypeScript, and Bash.

    No, this is a static analysis tool that audits code before installation to prevent attacks; it does not monitor the behavior of agents while they are actively running in your production environment.

    You will need Git for cloning remote repositories and Perl installed on your host system to power the high-speed pattern scanning engine.

    The tool generates a structured report with a 0-100 risk score and specific line-by-line citations of any red flags, concluding with a clear "OK," "Review," or "Do Not Install" verdict.

    New in Security