The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, such as source code, git diffs, and debugger output, to generate explanations. \n- Ingestion points: The skill reads code and diffs from the user's environment as specified in the instructions in SKILL.md. \n- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the processed data are defined in the skill instructions. \n- Capability inventory: The skill has the ability to invoke other skills (how, why, unslop) and use an image-generation tool based on its configuration. \n- Sanitization: There is no evidence of sanitization or filtering of the ingested content before it is incorporated into the agent's context.

teach