The Agent Skills Directory

[SAFE]: The skill is composed of markdown instructions and reference templates for document generation. It does not contain executable code or script files.
[NO_CODE]: No source code (Python, JavaScript, shell) is included in the skill package, eliminating risks associated with dynamic execution or malicious logic.
[CREDENTIALS_UNSAFE]: No hardcoded credentials, API keys, or secrets were found. The skill does not access sensitive local file paths (e.g., .ssh, .aws).
[EXTERNAL_DOWNLOADS]: There are no network-based operations, external downloads, or remote code execution patterns present in the analyzed files.
[PROMPT_INJECTION]: The instructions do not contain patterns intended to bypass safety filters, override system prompts, or extract internal configuration.
[DATA_INGESTION]: The skill ingests data from local context files (product-marketing-context.md). While it lacks explicit boundary markers or sanitization for this input, the risk is negligible as the skill lacks any dangerous capabilities (network, shell, or sensitive file access) that could be exploited via indirect injection. Ingestion points: .agents/product-marketing-context.md or .claude/product-marketing-context.md. Capability inventory: No tools or shell access. Boundary markers: Absent. Sanitization: Absent.

sales-enablement