v1.0.0

Cold Call Script Generator

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 1:36 AM.

Analysis

This instruction-only sales writing skill appears coherent and benign, but it uses public prospect research and persuasive outreach techniques that should be reviewed for accuracy, privacy, and compliance.

GuidanceThis skill is reasonable to use as a drafting aid for sales outreach. Before using generated copy, verify all prospect facts, avoid overly personal or sensitive references, keep claims truthful, and make sure any calls or emails comply with your organization’s policies and applicable outreach laws.

Findings (4)

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityInfoConfidenceMediumStatusNote

SKILL.md

Before writing a single line, the agent gathers (or asks for) signal.

The skill may direct the agent to collect public prospect information from listed sources, which is aligned with sales-script personalization but should remain limited to user-approved, legitimate research.

User impactIf the agent has browsing or research tools available, it may use them to gather prospect context before drafting scripts.

RecommendationUse only approved sources, avoid scraping or private areas, and review any researched facts before using them in outreach.

Agentic Supply Chain Vulnerabilities

SeverityInfoConfidenceMediumStatusNote

metadata

Source: unknown; Homepage: none

The registry metadata does not provide an external source or homepage for provenance review. Because this is instruction-only with no code or install dependencies, this is a low-impact provenance note rather than a material concern.

User impactUsers have limited external provenance information about who authored or maintains the skill.

RecommendationReview the skill text before use and prefer skills with clear provenance for higher-trust workflows.

Human-Agent Trust Exploitation

SeverityLowConfidenceHighStatusNote

SKILL.md

Pattern interrupt > Permission > Value Tease

The skill explicitly teaches persuasive cold-outreach framing. This is central to the stated sales purpose and includes permission-based language, but users should ensure the resulting outreach is truthful and not manipulative.

User impactThe generated scripts may influence prospects through sales psychology and personalization, which can affect recipient trust if claims are exaggerated or context is misused.

RecommendationKeep outreach honest, identify yourself clearly, avoid fabricated familiarity or urgency, and comply with applicable calling and email rules.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Memory and Context Poisoning

SeverityLowConfidenceHighStatusNote

SKILL.md

LinkedIn profile | Tenure, prior roles, recent posts, mutual connections

The skill asks the agent to use prospect-specific public context, including personal/professional details, to personalize scripts. This is purpose-aligned, but the information can be sensitive or inaccurate if over-trusted.

User impactGenerated outreach may include personal or professional details about prospects; inaccurate or overly personal references could create privacy, trust, or compliance issues.

RecommendationVerify prospect facts, avoid sensitive personal details, and do not store or reuse prospect context beyond the intended outreach task unless allowed.