The Agent Skills Directory

[Prompt Injection] (SAFE): No patterns of instruction override, jailbreaking, or system prompt extraction were detected in the instructions.
[Data Exposure & Exfiltration] (SAFE): The skill does not access sensitive local file paths or perform unauthorized network requests. It correctly demonstrates restoring environment variables and global fetch states to ensure test isolation.
[Obfuscation] (SAFE): No Base64, zero-width characters, homoglyphs, or other encoding techniques were used to hide malicious commands.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not download or execute remote scripts. It uses standard bun test CLI commands for its intended purpose.
[Privilege Escalation] (SAFE): No commands for acquiring administrative privileges (e.g., sudo, runas) were found.
[Persistence Mechanisms] (SAFE): No attempts to modify startup files, shell profiles, or scheduled tasks were identified.
[Indirect Prompt Injection] (SAFE): The skill provides templates for test code. It does not ingest untrusted data from external sources that could lead to injection attacks.
[Dynamic Execution] (SAFE): The use of await import() in code examples is a standard requirement for Bun's mock.module() feature to ensure modules are loaded after mocks are initialized. This is a legitimate use within the primary purpose of the skill and poses no risk.

bun-test