The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8). It is designed to ingest and analyze untrusted source code from a project directory. If the analyzed code contains malicious instructions, the agent could potentially be diverted from its intended task.
Ingestion points: The skill utilizes Read, Grep, and Glob tools to access and analyze the contents of local files.
Boundary markers: There are no specific instructions or delimiters provided to help the agent distinguish between code-to-be-analyzed and potential malicious instructions embedded within that code.
Capability inventory: The skill is granted access to the Bash tool, which presents a high-risk capability if the agent is successfully manipulated by an indirect prompt injection.
Sanitization: There are no explicit steps for sanitizing, escaping, or validating the input data before it is processed by the agent.

rightcode-codeprobe-performance