The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and processing untrusted English text and local file content provided by the user, which presents an indirect prompt injection surface.
Ingestion points: SKILL.md specifies that the agent should read target text provided by the user and potentially read entire files if a path is identifiable to gather context.
Boundary markers: The instructions do not specify the use of clear delimiters or guardrails to prevent the agent from obeying instructions that might be embedded within the English text being explained.
Capability inventory: The skill requires the agent to read files and codebase context, but it does not perform network operations or file writes.
Sanitization: There is no evidence of input sanitization or validation of the text/file content before it is incorporated into the agent's context for explanation.

en-explainer