Skillv1.0.0

ClawScan security

Filtrix Image Generation · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

ReviewFeb 24, 2026, 8:15 AM

Verdict: Review
Confidence: medium
Model: gpt-5-mini
Summary: The skill implements the advertised multi-provider image generation functionality, but registry metadata and SKILL.md disagree about required credentials and the package includes executable scripts from an unknown source — review keys and code before using.
Guidance: This skill appears to do what it says (multi-provider image generation) but has a few transparency issues you should address before installing: 1) The SKILL.md and included scripts require API keys (OPENAI_API_KEY, GOOGLE_API_KEY, FAL_KEY) but the registry metadata doesn't declare them — expect to provide those keys as environment variables. 2) The package contains executable Python scripts from an unknown source and no homepage; review the scripts (generate.py and edit.py) yourself or run them in an isolated environment. 3) Use non-production or limited-permission API keys where possible, because keys can incur charges when used. 4) If you need stronger assurance, ask the publisher for a homepage, contact information, or a signed release, or run the code in a sandbox and test with dummy keys first. If you accept these caveats, the functionality is coherent; if not, do not install or run the scripts.

Review Dimensions

Purpose & Capability: concernThe skill's code and SKILL.md clearly implement image generation/editing via OpenAI, Google Gemini, and fal.ai and legitimately need provider API keys. However, the registry metadata lists no required environment variables or primary credential while the SKILL.md and scripts require OPENAI_API_KEY, GOOGLE_API_KEY, and FAL_KEY. That metadata omission is an inconsistency that reduces transparency.
Instruction Scope: noteThe SKILL.md instructions are scoped to generating or editing images and explicitly tell the agent to use the included scripts and set provider API keys. The scripts only access user-supplied image files, the declared provider APIs, and the filtrix.ai prompts page. One operational note: the scripts will fetch image URLs returned by providers (i.e., they may download remote content the provider returns), which is expected for this domain but worth knowing.
Install Mechanism: noteThere is no install spec (lowest risk), and the code claims no pip dependencies and indeed uses only Python stdlib. However, the package includes two executable Python scripts (generate.py, edit.py) that will run locally — the lack of an install step doesn't remove execution risk from arbitrary code bundled with the skill.
Credentials: concernThe environment/credential requirements in the SKILL.md (OPENAI_API_KEY, GOOGLE_API_KEY, FAL_KEY) are proportionate to the stated purpose. The problem is registry metadata not declaring these required env vars or a primary credential, which is misleading. Also note: these API keys are billing-capable credentials for third-party services — granting them lets the skill perform networked calls that may incur charges.
Persistence & Privilege: okThe skill is not always-enabled and is user-invocable; it does not request persistent system-wide privileges, nor does it modify other skills or system configuration. Autonomous invocation is allowed (platform default) but not combined with any other elevated privilege here.