The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions attempting to override agent behavior, bypass safety filters, or extract system prompts were detected.
[Data Exposure & Exfiltration] (SAFE): The skill emphasizes the use of environment variables and secret stores (AWS KMS, Vault) for sensitive data. No hardcoded credentials or unauthorized network exfiltration patterns were found.
[Obfuscation] (SAFE): No Base64, zero-width characters, homoglyphs, or other obfuscation techniques were identified in the markdown or metadata.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): Recommended packages (e.g., libcluster, Oban, opentelemetry_phoenix) are standard, well-established libraries in the Elixir ecosystem. No suspicious remote code execution patterns (like curl | bash) are present.
[Privilege Escalation & Persistence] (SAFE): The skill does not contain commands for sudo access, service installation with elevated privileges, or persistence mechanisms like crontabs or shell profile modifications.
[Indirect Prompt Injection] (SAFE): The skill focuses on static configuration and deployment documentation; it does not present an attack surface for ingesting untrusted external data into the agent's prompt context.

phoenix-ops