Back to skill
Skillv1.0.0
ClawScan security
Eo Ability Architect · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 7, 2026, 4:00 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only architecture-advice skill that is internally consistent with its stated purpose and does not request extra credentials, binaries, installs, or unusual privileges.
- Guidance
- This skill is instruction-only and appears coherent: it doesn't request secrets or install anything. Before using, be aware that its architecture recommendations are LLM-driven unless you have the EO ecosystem plugins it references; verify any high-risk design decisions with human experts. Also note that, as an agent skill, it can be invoked by automated agents or other EO plugins — ensure you trust those callers and review outputs for sensitive information before sharing externally.
Review Dimensions
- Purpose & Capability
- okName/description match the content of SKILL.md: the skill provides architecture design, tech selection, risk assessment and complexity estimates. Nothing in the metadata or instructions asks for unrelated resources (cloud keys, system access, etc.).
- Instruction Scope
- okSKILL.md only specifies how to invoke the architect capability, example inputs/outputs, and example text/diagrams. It does not instruct the agent to read local files, access environment variables, send data to unknown endpoints, or perform actions outside the stated purpose.
- Install Mechanism
- okNo install spec and no code files — instruction-only. No downloads, package installs, or archive extraction are specified.
- Credentials
- okThe skill requires no environment variables, no credentials, and no config paths. Declared requirements are proportional to an LLM-based architecture advisor.
- Persistence & Privilege
- okalways is false and there are no special persistence or system-wide configuration changes described. The skill is user-invocable and can be called autonomously by agents (platform default), which is expected for a skill.