CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

commit-guards

Load to add, tune, or debug a commit guard lane, its git hooks, or COMMIT_GUARDS_* settings.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security
Medium

W013: Attempt to modify system services in skill instructions.

What this means

The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.

Why it was flagged

The skill arms git hooks inside the repository's own `.git` directory, which is project-scoped, needs no sudo, and touches no system files, accounts, or SSH/systemd config; it also asks for owner consent first, so it mostly falls under the project-specific exception, though the persistent hook changes affecting all committers warrant a moderate score under recall-first.

Report incorrect finding
Low

W011: Third-party content exposure detected (indirect prompt injection risk).

What this means

The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.

Why it was flagged

The required workflow reads git index and diff content, including changelog fragment text (echoed as `entry-preview=`) and markdown, but that content is only outsider-authored if it arrives via a commit range or PR branch the agent chooses to check, so it is low rather than medium.

Low

W012: Unverifiable external dependency detected (runtime URL that controls agent).

What this means

The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.

Why it was flagged

The skill instructs the agent to read a remote GitHub DEVELOPMENT.md as install-contract guidance before installing or repairing hooks, so that content governs setup behavior, and its publisher (vanillagreencom/kendex) is an individual or project-owned repository without established strong first-party provenance, making it a common/reputable unofficial dependency (medium).

Repository

vanillagreencom/kendex

Path

.agents/skills/commit-guards/SKILL.md

Audited
Security analysis
Snyk

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.