The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown documentation and YAML metadata. No executable scripts, binaries, or active code components are present, which minimizes the attack surface.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external project files, such as CONTEXT.md, to match domain language. This represents a potential surface for indirect prompt injection where a malicious project file could attempt to influence agent behavior. However, this is considered safe in this context as the skill does not grant the agent high-privilege capabilities or tools that could be exploited through this ingestion.
[SAFE]: Comprehensive analysis detected no evidence of prompt injection, data exfiltration, obfuscation, or malicious persistence mechanisms. The included code snippets are benign educational examples of TypeScript testing patterns.

tdd