The Agent Skills Directory

[DYNAMIC_CONTEXT_INJECTION]: The skill uses the !command syntax to execute shell commands (cat) at load time to pull in protocol files and configuration files such as .production-grade.yaml and .forgewright/settings.md. These operations are used to provide the agent with necessary context and do not involve untrusted input or sensitive system paths.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data, including competitor URLs and product documentation (BRD/PRD). While this creates a surface for indirect prompt injection where instructions hidden in a website or document could influence the agent, the skill follows standard marketing workflows.
Ingestion points: External URLs, competitor websites, and product requirement documents.
Boundary markers: None explicitly defined in the instructions.
Capability inventory: File system writes to the marketing/ directory.
Sanitization: No specific sanitization or filtering of external content is described.

growth-marketer