Skip to content
Back to the index

SkillTrace

PyPIInfrastructure

PulseGate's liveness check found it on 14 Oct 2026; it is registered on GitHub and PyPI and has been in the index since 8 Aug 2026. How this is checked

SkillTrace is an open-source behavioral scanner for agent skills used with Claude, Cursor, and Codex. It sandboxes skill execution and traces actual behavior to help developers assess potentially unsafe or misleading skills.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI
1star
5features
2026since

Overview

5 features

Purpose: Verifying what agent skills actually do before allowing them to run in a development environment.

Inferred · not functionally tested

Audience: AI agent developers and security-conscious developers

Inferred · not functionally tested

Functions: Unknown

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

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

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

SkillTrace sits in PulseGate's AI & LLM security category. Inferred · not functionally tested: It focuses on verifying what agent skills actually do before allowing them to run in a development environment. Inferred · not functionally tested: It is built as an open-source project for AI agent developers and security-conscious developers. Basis unknown · not verified: SkillTrace is open source under the MIT license. Basis unknown · not verified: SkillTrace is available on the command line, and it can be self-hosted.

It is developed by handcraftedbygod, and it first shipped in 2026. The project is developed in the open on GitHub with 66 commits in the last 90 days. Inferred · not functionally tested: Among its 5 catalogued features are skill sandboxing, behavior tracing, and agent skill scanning.

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

Tasks: Inferred · not functionally tested

  • Skill sandboxing
  • Behavior tracing
  • Agent skill scanning
  • Permission analysis
  • Execution monitoring

Topics: Inferred · not functionally tested

Tags
agent-securityskill-sandboxingbehavioral-scanningexecution-tracing

JSON profile · Text profile · Access guide

Built with & integrations

Connectors
github
Runs on
CLISelf-hosted

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceFree tierGitHub · ★ 1Active maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed8 Aug · 00:00 UTC
    skilltrace seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about SkillTrace

What is SkillTrace?
Inferred · not functionally tested: SkillTrace focuses on verifying what agent skills actually do before allowing them to run in a development environment. It is catalogued under AI & LLM security on PulseGate.
Who is SkillTrace for?
Inferred · not functionally tested: SkillTrace is an open-source project built for AI agent developers and security-conscious developers.
Does SkillTrace have a free plan?
Basis unknown · not verified: Yes — SkillTrace is open source under the MIT license and free to use.
What platforms does SkillTrace run on?
Basis unknown · not verified: SkillTrace runs on the command line. It can also be self-hosted.
Is SkillTrace still maintained?
PulseGate's liveness check found it on 14 Oct 2026. Its GitHub repository shows 66 commits in the last 90 days.
What projects are similar to SkillTrace?
Similar projects tracked by PulseGate include skillscan-trace, SkillScan, and skillstat.skillscan-traceSkillScanskillstat
Who makes SkillTrace?
SkillTrace is developed by handcraftedbygod.
When did SkillTrace launch?
SkillTrace first shipped in 2026.

Similar projects

Closest matches by what these projects do

Submit to the index
Apps, agents and models — free, no signup.