The Agent Skills Directory

[Indirect Prompt Injection] (SAFE): The skill possesses an attack surface for indirect prompt injection because it processes external source code provided by the user and has the capability to modify files.
Ingestion points: Processes files and directories via the target argument in SKILL.md.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are present in the prompt instructions.
Capability inventory: Utilizes MultiEdit for batch file modifications and TodoWrite for tracking changes.
Sanitization: No explicit sanitization or validation logic is defined for the ingested code content. Note: This risk is inherent to the primary purpose of a code refactoring tool and is considered acceptable in this context.

sc-improve