The Agent Skills Directory

[SAFE]: The skill is primarily instructional, offering templates and strategic advice for marketing tasks. No high-risk operations such as network requests, credential access, or privilege escalation were detected.
[INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read external context files if present in the environment (e.g., .agents/product-marketing.md). While this creates an ingestion point for untrusted data, it is a standard mechanism for agent context discovery.
Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md (specified in SKILL.md).
Boundary markers: None explicitly defined for the ingested files.
Capability inventory: No risky capabilities (subprocess, file-write, network) are defined in the provided files.
Sanitization: No content sanitization logic is implemented for the ingested data.

lead-magnets