Homepage

hermes-agent@0.13.0

The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere

  • latest version

    0.18.0

  • latest non vulnerable version

    0.18.0

  • first published

    1 months ago

  • latest version published

    3 days ago

  • licenses detected

  • View hermes-agent package health on Snyk  (opens in a new tab)
    • Go back to all versions of this package
    Report a new vulnerability Found a mistake?

    Direct Vulnerabilities

    Known vulnerabilities in the hermes-agent package. This does not include vulnerabilities belonging to this package’s dependencies.

    Fix vulnerabilities automatically

    Snyk's AI Trust Platform automatically finds the best upgrade path and integrates with your development workflows. Secure your code at zero cost.

    Fix for free
    VulnerabilityVulnerable Version
    • M
    Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

    hermes-agent is a The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere

    Affected versions of this package are vulnerable to Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection') in the Skills Guard Multi-Word Prompt Handler process in the file agent/skills_guard.py when handling the THREAT_PATTERNS argument. An attacker can execute arbitrary code or commands by supplying crafted input remotely.

    How to fix Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')?

    Upgrade hermes-agent to version 0.15.0 or higher.

    [,0.15.0)
    • M
    Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

    hermes-agent is a The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere

    Affected versions of this package are vulnerable to Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection') via the _scan_context_content function. An attacker can execute arbitrary code or inject malicious input by supplying crafted data to this function.

    How to fix Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')?

    Upgrade hermes-agent to version 0.15.0 or higher.

    [,0.15.0)
    • H
    Missing Authentication for Critical Function

    hermes-agent is a The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere

    Affected versions of this package are vulnerable to Missing Authentication for Critical Function in the handling of WebSocket upgrade requests on /api/pty, /api/ws, /api/pub, and /api/events endpoints due to the FastAPI HTTP middleware not executing for these requests. An attacker can bypass access controls by exploiting DNS rebinding, which may allow the injection of malicious commands or reading of terminal output.

    How to fix Missing Authentication for Critical Function?

    Upgrade hermes-agent to version 0.16.0 or higher.

    [,0.16.0)
    • M
    Incorrect Default Permissions

    hermes-agent is a The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere

    Affected versions of this package are vulnerable to Incorrect Default Permissions due to the creation of response_store.db and webhook_subscriptions.json files with world-readable permissions. An attacker can access sensitive data, such as conversation history, tool payloads, prompts, and HMAC secrets, by reading these files directly if they have local filesystem access.

    How to fix Incorrect Default Permissions?

    Upgrade hermes-agent to version 0.16.0 or higher.

    [,0.16.0)
    Go back to all versions of this package