Skip to content
Back to the index

harnessguard

PyPIInfrastructure

PulseGate's liveness check found it on 14 Sep 2026; it is registered on PyPI and has been in the index since 14 Sep 2026. How this is checked

HarnessGuard is an Apache-2.0 static linter for GitHub Actions workflows that run AI agents. It checks workflows against the Agent Rule of Two and maps findings to OWASP ASI, producing security-oriented results without executing the workflows.

Inferred · not functionally tested

Open SourceApache-2.0CLISelf-hosted
Visit PyPI

Overview

6 features

Purpose: Hardening AI-agent GitHub Actions workflows against prompt injection, supply-chain, and other security risks.

Inferred · not functionally tested

Audience: developers and security engineers building AI-agent workflows

Inferred · not functionally tested

Functions: monitoring

Inferred · not functionally tested

Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: Apache-2.0 · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org. These links do not verify the individual claims.

harnessguard sits in PulseGate's AI & LLM security category. Inferred · not functionally tested: It focuses on hardening AI-agent GitHub Actions workflows against prompt injection, supply-chain, and other security risks. Inferred · not functionally tested: It is built as an open-source project for developers and security engineers building AI-agent workflows. Basis unknown · not verified: harnessguard is open source under the Apache-2.0 license. Basis unknown · not verified: It ships for the command line, and it can be self-hosted.

harnessguard first shipped in 2026. Inferred · not functionally tested: Key capabilities include workflow linting, AI agent checks, and OWASP ASI mapping.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Workflow linting
  • AI agent checks
  • OWASP ASI mapping
  • Prompt injection checks
  • SARIF output
  • Supply-chain analysis

Topics: Inferred · not functionally tested

Tags
github-actionsai-agent-securityprompt-injectionsupply-chain-securitysast-linter

JSON profile · Text profile · Access guide

Built with & integrations

Connectors
github
Runs on
CLISelf-hosted

Trust & compliance

License
Apache-2.0
Public signals
HTTPSOpen SourceFree tier

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed14 Sep · 14:28 UTC
    harnessguard seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open

Frequently asked questions about harnessguard

What is harnessguard?
Inferred · not functionally tested: Harnessguard focuses on hardening AI-agent GitHub Actions workflows against prompt injection, supply-chain, and other security risks. It is catalogued under AI & LLM security on PulseGate.
Who is harnessguard for?
Inferred · not functionally tested: harnessguard is an open-source project built for developers and security engineers building AI-agent workflows.
Does harnessguard have a free plan?
Basis unknown · not verified: Yes — harnessguard is open source under the Apache-2.0 license and free to use.
What platforms does harnessguard run on?
Basis unknown · not verified: harnessguard runs on the command line. It can also be self-hosted.
Is harnessguard still active?
PulseGate's liveness check found it on 14 Sep 2026.
What are alternatives to harnessguard?
Similar projects tracked by PulseGate include warrantor-harness, harnesslab, and hol-guard.warrantor-harnessharnesslabhol-guard
When did harnessguard launch?
harnessguard first shipped in 2026.
Is harnessguard open source?
Basis unknown · not verified: Yes — harnessguard is open source under the Apache-2.0 license.

Similar projects

Closest matches by what these projects do