The Agent Skills Directory

[NO_CODE]: The skill is composed strictly of markdown documentation and instructions. It does not define any tools, scripts, or configuration files that could be executed or misconfigured.
[INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting untrusted data (code snippets, bug reports, and environment context) which represents an attack surface for indirect prompt injection. However, the skill lacks any capabilities to perform actions like network requests, file modifications, or command execution, neutralizing the risk. Ingestion points: Processes external code, issue descriptions, and logs in the 'To Prompt' workflow. Boundary markers: None specified in the instructions. Capability inventory: No tools or scripts defined. Sanitization: None specified.

to-prompt