The Agent Skills Directory

[SAFE]: The skill content is entirely instructional, providing frameworks for partner identification, campaign planning, and outreach. No scripts or executable code (Python, Node.js, or Shell) are included.
[SAFE]: No obfuscation techniques, such as Base64 encoding, zero-width characters, or homoglyphs, were found in the skill body or metadata.
[SAFE]: The skill does not perform any network operations or access sensitive system files. References to external tools like Crossbeam and PartnerStack are for informational purposes and link to local documentation files.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read context from local files like .agents/product-marketing.md. While this represents a data ingestion surface, the skill lacks any dangerous capabilities (such as writing to the file system or making external network requests) that could be exploited via malicious content in those files.

co-marketing