The Agent Skills Directory

[SAFE]: The skill consists of markdown instructions and templates for text transformation tasks. No malicious patterns, obfuscation, or unauthorized access attempts were identified. All external links point to legitimate tool landing pages or public repositories.
[DATA_EXPOSURE]: The skill instructions include reading project-specific marketing context files (e.g., .agents/product-marketing.md). This is standard practice for providing agent context and does not involve access to sensitive system files or credentials.
[INDIRECT_PROMPT_INJECTION]: The skill processes external pillar assets (reports, blog posts) provided by the user, which constitutes an ingestion point for untrusted data. However, the skill includes explicit 'no-fabrication' guardrails and boundary instructions that require the agent to reuse only what the source actually says, mitigating the risk of following embedded malicious instructions. The capability inventory is restricted to text generation, presenting a low-risk profile.

content-repurposing