The Agent Skills Directory

[SAFE]: The skill performs text and image processing within the agent's context and does not request any network, file system, or administrative permissions.\n- [NO_CODE]: The skill is comprised of natural language instructions and does not include any executable scripts or external dependencies.\n- [PROMPT_INJECTION]: The skill ingests untrusted data from user-uploaded images and grocery lists, which presents a surface for indirect prompt injection. Mandatory Evidence Chain: 1. Ingestion points: SKILL.md (aisle sign images and text grocery lists). 2. Boundary markers: Absent. 3. Capability inventory: No subprocess, network, or file-write capabilities. 4. Sanitization: Absent. The risk is negligible as the skill lacks exploitable tools.

sorting-groceries