The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's 'Memory Protocol' instructs the agent to execute shell commands to read from the path .claude/context/memory/learnings.md to maintain context across sessions.
[INDIRECT_PROMPT_INJECTION]: The skill functions as a code reviewer, which involves ingesting potentially untrusted data from the user's project files.
Ingestion points: The agent is instructed to read and analyze project source code using tools like Read, Grep, and Glob.
Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between user-provided code and system instructions.
Capability inventory: The skill is granted extensive permissions, including the ability to execute Bash commands and use Write or Edit tools.
Sanitization: There are no defined mechanisms for sanitizing or validating the content of the files processed during code reviews.

frontend-expert