The Agent Skills Directory

[SAFE]: The skill follows standard instructional practices for marketing automation and growth strategy. It provides well-defined frameworks and metrics without requesting excessive permissions or performing dangerous operations.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from context files such as .agents/product-marketing.md. While this creates an attack surface for indirect prompt injection (where instructions hidden in marketing context files could attempt to influence the agent), the skill does not possess high-risk capabilities like arbitrary command execution or network exfiltration that would allow for exploitation. The ingestion is limited to providing better domain-specific advice.
[DATA_EXPOSURE_AND_EXFILTRATION]: No evidence of credential harvesting or data exfiltration was found. The skill references external marketing tools but does not attempt to send sensitive user information or hardcoded secrets to unauthorized domains.
[COMMAND_EXECUTION]: There are no shell commands or subprocess calls identified in the provided files. The skill functions entirely as a text-based advisor for marketing programs.

referrals