Action Suggester
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill appears benign: it drafts follow-up suggestions for review and explicitly says not to send, execute, store, or approve actions.
This skill looks suitable for generating non-binding follow-up recommendations, but treat lead names and phone numbers as sensitive business/customer data and review suggestions before anyone calls, emails, visits, or updates a system.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
You have less external provenance information about who maintains the skill, but there is no code-install behavior shown here.
The skill's public provenance is limited. This matters for trust decisions, though the artifact set is instruction-only and includes no executable code, install script, or dependency chain.
Source: unknown; Homepage: none
Install only if you trust the registry publisher and the plain-language instructions match your intended use.
Lead names and phone numbers may be included in prompts or context while generating suggestions.
The skill is designed to process lead records that include personal contact details in the model context. The artifacts do not show storage, external transmission, or reuse, and this data is aligned with the follow-up suggestion purpose.
"required": ["lead_id", "name", "phone"]
Use only lead data you are authorized to process, and avoid including unnecessary personal details beyond what is needed for the suggestion task.