The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes research findings and previous reports to generate marketing documents, creating a surface where malicious instructions in those sources could influence the agent's behavior. \n- Ingestion points: The skill reads data from brand_knowledge_search, knowledge_search, and local folders gooseworks-local/ and gooseworks-reports/. \n- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified in the report generation workflow. \n- Capability inventory: The agent is instructed to write files to the local filesystem and use the save-to-brain skill. \n- Sanitization: No sanitization or validation of the ingested findings is required by the instructions. \n- [COMMAND_EXECUTION]: The skill directs the agent to perform file system operations to save generated reports. \n- Evidence: SKILL.md §2 instructions include writing Markdown files to gooseworks-reports/<brand-slug>/.

write-report