ClawHub
Back to skill

Security audit

Git Commit Message Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for drafting conventional commit messages from staged Git diffs, with disclosed optional tooling setup risks but no hidden or automatic harmful behavior found.

Before installing, understand that the core skill reads staged Git diffs to draft commit messages. Treat generated messages as suggestions and review them before committing. If you use the optional integrations, prefer project-local pinned dev dependencies over global npm installs, and avoid running install commands with elevated privileges.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:400
Finding

Unpinned Global npm Package Installation Creates Supply-Chain Risk

Content
View full analysis
Remediation
View remediation
\ @commitlint/config-conventional@ \ husky@ \ semantic-release@ \ conventional-changelog-cli@ ``` 2. Pin exact reviewed versions rather than mutable version ranges. 3. Commit `package-lock.json` and use `npm ci` so dependency resolution is reproducible. 4. Review package provenance, maintainers, lifecycle scripts, and transitive dependencies before adoption. 5. Use `npm audit`, dependency monitoring, and lockfile-integrity checks in CI. 6. Where compatible with the selected packages, use `npm ci --ignore-scripts` and explicitly run only required, reviewed setup steps. 7. Invoke local binaries through package scripts or `npx --no-install` instead of installing global executables. 8. Clearly mark these integrations as optional and state that the core Skill requires only Git. 9. Warn users not to run npm installation commands with `sudo` or another elevated account. ]]>

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · EXAMPLES.md (reported line 344)May include surrounding context.

md
feat(auth)!: change login API to return auth result object

Updates login function to accept credentials object and return
structured auth result with access token, refresh token, and
expiration time. Enables future extensions like device tracking.

BREAKING CHANGE: login() signature changed from

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · COMMIT_TYPES_REFERENCE.md (reported line 237)May include surrounding context.

text
ci: add automatic deployment to staging

Adds GitHub Actions workflow to automatically deploy to
staging environment on merge to develop branch. Includes
smoke tests before deployment.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · EXAMPLES.md (reported line 287)May include surrounding context.

md
+
+ ```bash
+ curl -H "Authorization: Bearer YOUR_TOKEN" \
+   https://api.example.com/users
+ ```
+
+ ### Endpoints

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

Line L658 states that the skill 'learns from your project's patterns and adapts its messages to match your style over time.' In this file, the documented behavior is purely example-driven and there is no evidence of any persistent learning or adaptation mechanism; this is an active claim about behavior rather than a mere omission.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.