The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by ingesting existing repository configuration files and modifying agent-specific instruction files (CLAUDE.md or AGENTS.md).
Ingestion points: The agent is instructed to read existing .dependency-cruiser.* configuration files from the local filesystem during the environment detection phase.
Boundary markers: Absent; the skill does not provide delimiters or instructions to treat the ingested configuration as untrusted data during the merging process.
Capability inventory: The skill has the capability to execute shell commands via various package managers (npm, pnpm, yarn, bun) and perform file write operations for configurations and documentation.
Sanitization: Absent; the skill instructs the agent to merge existing configuration rules into the new setup without explicit validation or sanitization of the content.
[COMMAND_EXECUTION]: The skill executes shell commands to install the dependency-cruiser package and run the depcruise validation tool. These commands are necessary for the skill's primary function of enforcing code boundaries but represent a capability to run external binaries.

setup-ts-deep-modules