The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions specify the execution of 'make lint' and 'make test'. This allows for the execution of any commands defined in the project's Makefile, which could be exploited if the project source is untrusted.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing external code and Git commit data. Ingestion points: Git commit history and repository source files. Boundary markers: None present; the agent is not instructed to distinguish between its instructions and content within the code. Capability inventory: Shell command execution via 'make'. Sanitization: No sanitization or safety checks are performed on the Makefile or code content prior to execution.

code_review