The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and modify code comments within source files. This creates a surface for indirect prompt injection where an agent might inadvertently follow instructions embedded in comments of the code it is processing.
Ingestion points: External source code files accessed through Read, Glob, and Grep tools as defined in the skill metadata.
Boundary markers: The instructions do not define clear delimiters or "ignore" directives to prevent the agent from being influenced by instructions contained within the code comments it evaluates.
Capability inventory: The skill possesses Write and Edit capabilities, allowing it to modify files on the filesystem based on the content of the processed data.
Sanitization: No sanitization or validation mechanisms are described to filter or escape potential command strings found within the comments being analyzed.

antislop-code