The Agent Skills Directory

[COMMAND_EXECUTION]: The diagnostic script scripts/ts_diagnostic.py uses subprocess.run(shell=True) to execute shell commands such as npx tsc, node, and grep to check environment versions and perform type-checking diagnostics.
[COMMAND_EXECUTION]: The skill provides instructions for the agent to use bash commands to detect project tooling and monorepo configurations, including a Node.js one-liner to parse package.json dependencies.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to read and analyze user-controlled project files (e.g., tsconfig.json, package.json, and source code in the src/ directory).
Ingestion points: Reads project configuration files (tsconfig.json, package.json) and source files (via grep and Read tool) to provide diagnostics.
Boundary markers: No specific delimiters or warnings are used to wrap the content of ingested files to prevent the agent from following instructions embedded within them.
Capability inventory: The skill has the ability to execute shell commands via subprocess.run in scripts/ts_diagnostic.py and via the Bash tool as documented in SKILL.md.
Sanitization: There is no evidence of sanitization or filtering of the content read from files before it is processed by the agent.

typescript-expert