The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill functions as a dispatcher that ingests untrusted data in the form of source code and passes it to subagents for analysis, which represents an indirect prompt injection surface.
Ingestion points: The skill reads files from the project codebase identified in the {FILE_LIST} variable within SKILL.md.
Boundary markers: The subagent prompt template lacks explicit delimiters or specific instructions for the subagent to ignore instructions that might be embedded within the code being analyzed.
Capability inventory: The skill utilizes Glob and Grep tools for file discovery and the Task tool to execute subagents.
Sanitization: There is no evidence of sanitization, validation, or escaping of the code content before it is interpolated into subagent prompts.
[DYNAMIC_EXECUTION]: The skill dynamically constructs prompts for its subagents by interpolating variable data such as file lists, category names, and flag values into a static text template.

stride