The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from external rule files and an index. This represents a data ingestion surface where external content is incorporated into the agent's context during lookup.
Ingestion points: RULE_INDEX.md and reference files accessed via Read, Glob, and Grep tools.
Boundary markers: Absent; the instructions do not provide explicit delimiters or instructions to ignore embedded commands in the rule files.
Capability inventory: The skill is restricted to read-only tools (Read, Glob, Grep). It lacks capabilities for file modification, network operations, or shell execution.
Sanitization: Content is summarized and reported as found without specific filtering for instructions, though the risk is minimal given the restricted toolset.

find-rule