The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands in SKILL.md and a dedicated Python script scripts/ts_diagnostic.py to perform project diagnostics, version checks, and type checking.
The Python script uses subprocess.run() with shell=True to execute commands such as npx tsc, grep, and node -v.
SKILL.md instructs the agent to execute shell commands to detect monorepo configurations and tooling ecosystems by parsing package.json and checking for specific configuration files.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local environment, creating a surface for indirect prompt injection.
Ingestion points: The skill reads and parses package.json, tsconfig.json, and various configuration files (e.g., lerna.json, turbo.json). It also performs recursive grep operations on the src/ directory.
Boundary markers: There are no explicit instructions or delimiters used to prevent the agent from interpreting instructions that might be embedded in the project files or command outputs.
Capability inventory: The skill has the capability to execute shell commands (e.g., npm run, npx tsc, vitest) and run a Python script that spawns subprocesses.
Sanitization: There is no evidence of sanitization or validation of the content read from the project files before it is processed by the agent or the diagnostic script.

typescript-expert