The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it is designed to read and process untrusted content from source code files within a project.
Ingestion points: The skill utilizes Read, Grep, and Glob tools to extract text from various project files for analysis.
Boundary markers: There are no specific instructions to use delimiters or ignore instructions embedded within the scanned files (e.g., malicious instructions hidden in code comments).
Capability inventory: The skill has access to the Bash tool, which allows for potentially dangerous command execution if the agent is manipulated.
Sanitization: No explicit sanitization or pre-processing of file content is mandated before the agent processes it. This risk is inherent to the functionality of a code scanner and is considered a functional surface rather than a malicious defect.

codeprobe-security