Book a 30-minute demo →
Skill scan report

skill-creator

View on GitHub
49 Medium Automated analysis flagged 4 potential risk patterns.

What this skill does

Skill creation and validation tool for AgentSkills, used to author, review, and package skills with defined workflows and structure.

github/openclaw - Insecure File Handling - 385.8k stars

ThreatsInsecure File Handling Insecure File Packaging Insecure Module Loading Insecure Validation

Threat analysis

Insecure File Handling1 finding
Insecure File Packaging1 finding
Insecure Module Loading1 finding
Insecure Validation1 finding

Skill info

Nameopenclaw/skill-creator
Registrygithub
Versionc39abce
PURLpkg:github/openclaw/openclaw@c39abce?skill=skill-creator
Stars385.8k

Assessments (4)

Insecure File Handling1 finding HIGH
HIGH

Insecure File Handling via local-llm-review

scripts/test_package_skill.py

The test script creates temporary directories and files without proper sanitization or security checks, which could be exploited if not properly managed.
Insecure File Packaging1 finding MEDIUM
MEDIUM

Insecure File Packaging via local-llm-review

scripts/package_skill.py

The `package_skill` function creates a distributable `.skill` file without explicit checks for malicious content in the skill folder, potentially allowing the inclusion of harmful files.
Insecure Module Loading1 finding MEDIUM
MEDIUM

Insecure Module Loading via local-llm-review

scripts/test_package_skill.py

The test script dynamically loads modules using `types.ModuleType` and manipulates `sys.modules`, which could be exploited for module hijacking or injection attacks.
Insecure Validation1 finding LOW
LOW

Insecure Validation via local-llm-review

scripts/quick_validate.py

The `_parse_simple_frontmatter` function uses a minimal parser for YAML frontmatter, which may not handle all edge cases securely and could be vulnerable to injection attacks.

Badge

Add the Anomity scan badge for skill-creator to your README.

Anomity Skill Check badge

Markdown
[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/openclaw/skill-creator/)
HTML
<a href="https://anomity.ai/skills/github/openclaw/skill-creator/"><img src="https://anomity.ai/skills/badge.svg" alt="Anomity Skill Check"></a>
Image URL
https://anomity.ai/skills/badge.svg

How Anomity governs this at runtime

Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.

Book a 30-minute demo to see your own skill inventory.

Methodology and disputes

Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of skill-creator? Report an issue or request a rescan.

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok