The Agent Skills Directory

[SAFE]: The skill provides standard documentation for the official ApideckUnifySdk and does not contain malicious code or instructions.
[CREDENTIALS_UNSAFE]: No hardcoded credentials were found. The skill specifically promotes the use of environment variables and secrets managers for API keys, which is a security best practice.
[EXTERNAL_DOWNLOADS]: The skill references the official ApideckUnifySdk NuGet package. This is documented neutrally as a standard dependency from a well-known service.
[INDIRECT_PROMPT_INJECTION]: The skill handles data from external third-party connectors via the Apideck Unified API. This ingestion of untrusted data represents an attack surface for indirect prompt injection if the output is processed by an LLM. However, the skill follows standard programmatic patterns and this risk is inherent to the primary purpose of building integrations. Evidence chain: 1. Ingestion points: API response data from sdk.Crm.Contacts.ListAsync and similar calls in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: SDK network operations and console output throughout SKILL.md. 4. Sanitization: Not explicitly implemented in the documentation snippets.

apideck-dotnet