The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill directs the agent to read and interpret project Makefiles, creating a surface for indirect prompt injection if a Makefile contains malicious instructions. This is a standard risk for development tools interacting with project source code. * Ingestion points: Makefile (referenced in SKILL.md rules) * Boundary markers: None specified * Capability inventory: Execution of make targets via shell * Sanitization: None specified.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands via make. This is the primary intended function of the skill to facilitate standard software build and test workflows.

prefer-make