Back to skill
Skillv1.0.0
ClawScan security
Ai Discoverability Audit · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 17, 2026, 8:10 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is internally coherent: its instructions and required resources match the stated purpose of auditing a brand's visibility in AI search and it does not request unrelated access or install arbitrary code.
- Guidance
- This skill is instruction-only and appears coherent and low-risk. Before installing, consider: (1) the agent may need web access or a human to run the queries if browsing is disabled; (2) do not paste sensitive or private data (API keys, internal docs) into queries against external AI services; (3) be aware the audit depends on the current behavior and biases of external AI platforms and may need periodic re-runs; and (4) the skill includes an external booking link (commercial contact) — verify vendor trust if you plan to engage. If you need the agent to perform live queries, confirm your environment's browsing policy and data-handling rules first.
Review Dimensions
- Purpose & Capability
- okName and description match the content of SKILL.md and the provided query bank. The skill requires no binaries, credentials, or installs — appropriate for an instruction-only audit tool.
- Instruction Scope
- okRuntime instructions are limited to running or recommending queries against AI platforms, documenting results, scoring, and making recommendations. The instructions do not ask the agent to read system files, access unrelated environment variables, or transmit data to unexpected endpoints.
- Install Mechanism
- okNo install spec and no code files beyond markdown; nothing is written to disk or downloaded. This is the lowest-risk model for a skill of this type.
- Credentials
- okThe skill requests no environment variables, credentials, or config paths — proportional to the stated purpose of running queries and producing an audit.
- Persistence & Privilege
- okDefaults (always: false, model invocation allowed) are used. The skill does not request permanent presence or elevated privileges and does not modify other skills or system-wide settings.