The Agent Skills Directory

[PROMPT_INJECTION]: No instructions were found that attempt to bypass safety filters or override the agent's core behavior.- [DATA_EXFILTRATION]: No hardcoded credentials, sensitive file path access, or unauthorized network operations were detected.- [REMOTE_CODE_EXECUTION]: The skill does not perform any remote script downloads or arbitrary command execution via unknown sources.- [OBFUSCATION]: No Base64, zero-width characters, homoglyphs, or other obfuscation techniques were identified.- [INDIRECT_PROMPT_INJECTION]: The skill facilitates infrastructure management through structured MCP tools. While it processes user-provided environment and workspace configuration, it does not demonstrate unsafe interpolation of untrusted data into executable contexts.

manage-iacm