The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill directs the agent to investigate external sources such as official documentation and source code, creating a surface for instructions embedded in that content to influence the agent.\n * Ingestion points: External official documentation, source code, and first-party APIs as described in SKILL.md.\n * Boundary markers: The instructions lack explicit delimiters or warnings to treat external content as untrusted data.\n * Capability inventory: The agent is instructed to write findings to Markdown files within the repository (SKILL.md).\n * Sanitization: No sanitization or filtering logic is specified for the data retrieved from external sources.\n- [NO_CODE]: The skill consists entirely of natural language instructions and configuration files, containing no executable code, scripts, or binaries.

research