Security audit
Security checks for vulnerabilities and agentic risk
The bundled workflow creates local drafts without hidden access, but its script does not deliver the promised complete outline.
Expect substantial manual completion: the supplied brief does not match the script's keyword input, and generated output does not establish disclosure compliance. Use a dedicated output folder because outline.md is overwritten. The optional Windows app is unnecessary for the Python workflow and needs a separate security assessment; a matching hash alone does not establish safety.
The code supports keyword-based outline generation, but its output materially omits the landing-page structure and disclosure coverage central to the description. It produces a generic keyword content outline instead. Local input reads and output writes are supporting implementation details, and the supplied code shows no unrelated resource access or hidden capabilities.
Without declared permissions the skill's intent is opaque and cannot be validated.
The manifest promises hero, proof, offer, objection, FAQ, and required disclosure sections. L078–L084 instead generate one generic section per keyword with query-answering instructions, while L085–L087 append internal copywriting guardrails rather than page disclosures.
Every keyword section is instructed to include a US-specific detail, imposing a regional constraint regardless of the user's target audience. The file neither offers a locale choice nor explains why this general landing-page copywriting tool requires US localization.
No suspicious patterns detected.
