The Agent Skills Directory

[SAFE]: The skill does not perform any network operations, execute arbitrary commands, or access sensitive system files.
[PROMPT_INJECTION]: The skill instructions include a directive to read local files such as .agents/product-marketing.md to gain context. This creates a surface for indirect prompt injection if those files contain malicious instructions, as there are no explicit boundary markers or sanitization steps mentioned.
Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md.
Boundary markers: Absent.
Capability inventory: The skill generates text-based recommendations and audits; no restricted tools or dangerous system operations are explicitly invoked.
Sanitization: No filtering or sanitization of the ingested file content is specified.

onboarding