ooutreachskill
Analysis
This is an instruction-only outreach-writing skill with no code, install steps, credentials, or persistence, though users should review its broad activation wording and marketing claims before using it.
Findings (3)
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.
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.
Always trigger on mentions of: DM, outreach, cold email, cold message... always load it before writing any message.
The skill tells the agent to invoke it broadly for outreach and message-writing contexts. This is aligned with the skill purpose, but the wording is broad enough that users should ensure it does not override their intended tone or task.
When given a name + title + company, search the internet and return: Recent LinkedIn posts, interviews, podcasts, conferences, or published articles...
The skill directs the agent to use internet search for prospect research. This is expected for personalized outreach and asks for source URLs, but it still involves researching individuals and companies.
We run the world's largest organic short-form distribution network - 10B+ impressions/month... Geo-targeted. Verified. 10-25x cheaper than paid ads.
The templates contain strong marketing claims intended for outbound messages. They are purpose-aligned, but the artifacts do not provide substantiation for those claims.