The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes external, untrusted document content without proper isolation or sanitization.
Ingestion points: Document content is retrieved via the Read tool in the first step of the workflow.
Boundary markers: No delimiters or safety instructions are used to separate the document content from the agent's internal instructions.
Capability inventory: The skill utilizes Read, Write, Edit, and Skill tools, allowing it to modify files based on instructions found in the text it processes.
Sanitization: The instructions lack any mechanism to sanitize or filter the input data before processing.

humanize-it