The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it is designed to read and process external source code which may contain malicious instructions intended to manipulate the agent. \n- Ingestion points: Source code files accessed via Read, Grep, and Glob tools as defined in SKILL.md. \n- Boundary markers: No delimiters or protective instructions are provided to isolate analyzed code from the system prompt. \n- Capability inventory: The skill utilizes the Bash tool for potential command execution alongside file system tools. \n- Sanitization: No input validation or content filtering is performed on the ingested code strings.

code-review