The Agent Skills Directory

[PROMPT_INJECTION]: The skill defines a workflow where the agent searches for and processes external data. This creates an indirect prompt injection surface where untrusted content could potentially influence agent behavior. Ingestion points: Information gathered through the '定向搜集' (Targeted search) step in SKILL.md. Boundary markers: No specific delimiters or instructions to ignore embedded commands are included. Capability inventory: The skill is restricted to mapping and reasoning tasks and does not involve risky tools or file access. Sanitization: No sanitization methods are specified for the external content.
[NO_CODE]: The skill is composed of markdown-based instructions and does not contain any executable scripts or external package dependencies.

dig