Back to skill
Skillv1.0.0
ClawScan security
Ads Asset Generator · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 3, 2026, 2:17 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only ad creative/spec generator that is internally consistent with its description and does not request credentials, install code, or access unrelated resources.
- Guidance
- This skill appears coherent and low-risk because it is purely instruction text that generates ad creative briefs and requires no credentials or installs. Before using it in production: (1) validate any policy, billing, or targeting recommendations against your ad accounts and platform policies (the skill purposely notes you should not fabricate policy outcomes), (2) never paste sensitive credentials or account tokens into prompts, (3) test outputs on sample inputs to ensure the suggested specs match your creatives and measurement setup, and (4) if you enable autonomous invocation for an agent, monitor actions that lead to live spend — the skill can produce plans but cannot itself execute ad account operations.
Review Dimensions
- Purpose & Capability
- okThe name and description (generate ad asset specs for multiple ad platforms) match the SKILL.md's inputs, outputs, workflow, decision rules, and platform notes. Nothing in the metadata or instructions asks for unrelated access (cloud creds, system files, or other services).
- Instruction Scope
- okSKILL.md contains explicit input/output contracts, workflows, platform-specific guidance, guardrails, and examples; it does not instruct the agent to read files, environment variables, system state, or to send data to any external endpoint. Instructions remain within the stated purpose.
- Install Mechanism
- okNo install spec, no code files, and no downloads — the skill is instruction-only, which minimizes filesystem and supply-chain risk.
- Credentials
- okNo required environment variables, no credentials, and no config paths are declared or referenced by the SKILL.md. Requested access is proportionate (none) to the skill's purpose.
- Persistence & Privilege
- okalways is false and disable-model-invocation is false (normal). The skill does not request permanent presence, nor does it modify other skills or system settings. Autonomous invocation is allowed by default but does not amplify other red flags here.