The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands for repository testing and profiling, including bun test --coverage, pnpm test:profile, and pnpm test:slowest. It also uses rg (Ripgrep) to scan the codebase for skipped tests and stale code patterns.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository's source code and test results which could contain malicious instructions.
Ingestion points: Project source files under packages/**/src/**, test files (*.spec.ts, *.spec.tsx), and generated lcov.info coverage data.
Boundary markers: The instructions do not specify explicit delimiters or "ignore instructions" warnings when the agent reads and scores the content of these files.
Capability inventory: The skill can execute local shell commands (testing/profiling) and write artifacts (markdown maps, TSV files) to the docs/plans/ directory. It does not perform network operations or high-privilege system modifications.
Sanitization: There is no mention of escaping, filtering, or validating the content extracted from the source files before it is processed by the agent.

testing-review