The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute standard test runners including npm test, npx vitest, pytest, and go test. These commands are expected and necessary for the skill's primary function of writing and verifying tests.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from multiple external sources which could be manipulated by an attacker to influence the agent's output.
Ingestion points: The agent reads external content from firecrawl_search results, production error logs via sentry:search_issues, and database metadata via supabase:execute_sql.
Boundary markers: The instructions do not specify the use of delimiters or boundary markers when interpolating this external data into the agent's context.
Capability inventory: The agent has the ability to execute shell commands (test runners) and perform SQL queries.
Sanitization: There is no mention of sanitizing, escaping, or validating the data retrieved from external tools before it is used to generate test files.

test-unit