The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external local files to provide context for its responses. \n- Ingestion points: The SKILL.md file (lines 14-16) instructs the agent to search for and read files such as .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md at startup. \n- Capability inventory: The skill primary focus is on text-based strategy generation and community management advice. It does not include scripts for subprocess calls, file writing, or network operations. \n- Boundary markers: The instructions do not define boundary markers or instructions to ignore embedded commands when processing the content of these context files. \n- Sanitization: No sanitization, escaping, or validation logic is applied to the content ingested from the external context files. \n- [NO_CODE]: The skill contains only instructional Markdown, reference documentation, and configuration files. It does not include any executable scripts, binaries, or automated tasks.

community-marketing