The Agent Skills Directory

SAFE (SAFE): The skill consists of instructional markdown files that guide the user on how to use the Ninja build system. No malicious scripts, obfuscated code, or suspicious network operations were found. The external link provided is to the official ninja-build.org documentation.
COMMAND_EXECUTION (LOW): The skill lists numerous shell commands for invoking ninja and cmake. These are expected for a build system skill and represent standard developer workflows. Examples include ninja -j$(nproc) for parallelism and ninja -t browse for local dependency visualization.
INDIRECT_PROMPT_INJECTION (LOW):
Ingestion points: The skill assists in interpreting output from ninja commands and the content of build.ninja files.
Boundary markers: N/A; the skill is a reference guide.
Capability inventory: Facilitates local build command execution via the Ninja binary.
Sanitization: N/A.
Assessment: The risk is minimal as the skill describes standard local build processes and does not automate the execution of untrusted remote content.

ninja