Back to skill
Skillv1.0.0
ClawScan security
cold-email-writer · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 16, 2026, 11:15 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only cold-email writing skill whose declared purpose, runtime instructions, and resource requirements are coherent and proportional.
- Guidance
- This skill appears to be what it claims: a prompt/template engine for writing outreach emails. Before installing, consider: (1) privacy — do not paste sensitive personal data, proprietary details, or private customer lists into prompts you don't want stored or seen by others; (2) review all outputs before sending — the skill can generate persuasive copy that could be inappropriate, misleading, or non-compliant with anti-spam rules; (3) if you plan to connect this to an email-sending system, that integration (which would require credentials) is separate and should be evaluated on its own. If you want the agent to never call skills autonomously, change the agent/skill invocation settings on your platform; otherwise the default autonomous invocation alone is not a red flag for this particular skill.
Review Dimensions
- Purpose & Capability
- okThe name and description match the SKILL.md: it asks users for offer/prospect/goal information and returns draft emails. There are no unexpected environment variables, binaries, or config paths requested.
- Instruction Scope
- okThe SKILL.md contains only guidance for producing cold emails and prompts the user for contextual inputs. It does not instruct the agent to read files, access environment variables, call external endpoints, or collect unrelated system data.
- Install Mechanism
- okNo install spec or code files are present (instruction-only). This is the lowest-risk model: nothing is downloaded or written to disk by the skill itself.
- Credentials
- okThe skill requires no credentials, env vars, or config paths, which is proportionate for a text-generation/template skill.
- Persistence & Privilege
- okalways is false and the skill is user-invocable. The skill may be invoked autonomously by the agent (default platform behavior), but there are no additional privileges or persistent modifications requested.