liatrio-git-commit
Generates standardized Conventional Commit messages and executes safe git commits with pre-commit hooks and quality guardrails.
78
/ 100 · Grade C
C = 70–79
“I need to create well-structured, standardized git commit messages that follow Conventional Commits format and safely commit changes with quality checks.”
liatrio-git-commit earned Certified status with a trust score of 78/100 (Grade C). Adversarial testing produced 2 findings (2 high).
Trust Score Breakdown
Eight weighted signals composing the aggregate trust score
Scheme v2.0 · Weights provisional · Consumer confirmations and uptime use pipeline-derived baselines.
Findings
Security scan results, adversarial testing, and pipeline review
Security Scan — Cisco Skill Scanner
Adversarial Testing — 3 categories, 2 findings
The skill contains numerous 'Always' directives that establish persistent behavioral patterns without explicit termination conditions. These directives could influence the agent's behavior on unrelated tasks beyond the git commit workflow.
The skill establishes a context marker system that instructs the agent to 'Always begin your response with all active emoji markers, in the order they were introduced' without clear termination conditions. This could cause the agent to include these markers in responses to unrelated tasks.
Methodology v1.0 · 3 categories · ~55 attack patterns
Behavioral Fingerprint
Runtime performance baseline for drift detection
Samples
8
Error rate
0.0%
Peak memory
— MB
Avg CPU
—%
Response time distribution
Output size distribution
Fingerprint v1.0 · Baseline: Mar 28, 2026 · Status: baseline
Interface
Skill triggers and instruction summary
Activation
Activates when users ask to create a commit, write a conventional commit message, split broad changes into multiple commits, stage only parts of files, run pre-commit before committing, or perform a quick commit-time quality review
Handles git commit creation with conventional commit messages, commit boundary analysis, pre-commit hook execution, and quality reviews within a git repository
Does
Generate Conventional Commit format messages with type, scope, and subject
Analyze commit boundaries and recommend splitting large changes
Stage files selectively using git add -p for partial commits
Run pre-commit hooks without bypass flags
Perform quality reviews with severity classification (Critical, High, Medium, Low)
Apply AI attribution footers to all commits
Classify commit pressure into green/yellow/red zones based on file count and line changes
Auto-fix trivial pre-commit hook issues with up to 2 retries
Present structured commit plans and per-commit previews before execution
Does not
Use hook bypass flags like --no-verify or -n
Commit when Critical or High review issues are present without explicit user confirmation
Include unrelated files in commits
Stage entire files when only some hunks belong to the current commit boundary
Mention AI generation in commit subject or body text
Scope & Permissions
What this capability can and cannot access — derived from pipeline analysis
no
no
yes
no
yes
no
Known Failure Modes
Documented edge cases and recovery behaviors
when when pre-commit hooks fail after 2 retries
then the agent stops and asks the user for direction
when when Critical or High severity issues are found in quality review
then the agent stops and requests explicit user confirmation before committing
when when changes exceed red zone thresholds (>12 files or >400 lines)
then the agent requires a split plan before proceeding with single commit
when when conventional commit message format is invalid
then the agent regenerates until format is valid
Badge & Integration
Embed certification status in your README, docs, or CI pipeline
Certification Notes
Provenance observations from the pipeline
Publisher "liatrio-labs" is not verified — first certification from this publisher
Single contributor — no peer review evidence in commit history
Repository is 19 days old — recently created
Package description appears to be boilerplate or template text
Signed Artifact
Certification provenance and verification metadata
Pipeline Artifacts
Raw data files from this certification run — downloadable for independent verification
contract.json
Full unsigned contract
stage1-ingest.json
Ingest stage output
stage2a-sbom.json
SBOM generation results
stage2a-vulns.json
Vulnerability scan results
stage2b-security.json
Security scan results
stage3a-functional.json
Functional test results
stage3b-adversarial.json
Adversarial test results
stage3c-fingerprint.json
Behavioral fingerprint
stage4-certify.json
Certification decision + trust score
stage3a-measurements.json
Raw functional test measurements
stage3b-measurements.json
Raw adversarial test measurements
run-log.json
Pipeline execution log
Not all files may be present for every certification.