The Agent Skills Directory

[CREDENTIALS_UNSAFE] (HIGH): The skill contains hardcoded credentials for test accounts and database access.
Evidence: Hardcoded Keycloak credentials testuser / testpassword.
Evidence: Hardcoded MySQL root password password1 in docker exec examples.
[COMMAND_EXECUTION] (HIGH): The skill provides patterns for executing arbitrary shell commands and direct database manipulation.
Evidence: Usage of node scripts/test-auth-route.js and docker exec -i local-mysql mysql.
[PROMPT_INJECTION] (HIGH): High risk of Indirect Prompt Injection (Category 8) due to the combination of untrusted data ingestion and powerful execution capabilities.
1. Ingestion points: The skill ingests untrusted JSON payloads and URL parameters for route testing.
1. Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands in the processed data.
1. Capability inventory: Includes shell script execution (node), database access (mysql), and environment configuration modification (.env).
1. Sanitization: Absent; the skill does not specify any sanitization, validation, or escaping for the external content before it is used in commands.

route-tester