apideck-rest
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the ingestion and processing of data from over 200 external services (e.g., Salesforce, QuickBooks, Workday) through the Apideck Unified API, establishing a surface for indirect prompt injection.
- Ingestion points: Data returned from GET requests to
https://unify.apideck.com(documented inSKILL.md). - Boundary markers: The instructions do not define any delimiters or warnings for the agent to ignore instructions that might be embedded within the data retrieved from external services.
- Capability inventory: The agent is guided to perform full CRUD operations (GET, POST, PATCH, DELETE) and handle webhooks, which could be exploited if malicious instructions are present in the ingested data.
- Sanitization: No guidelines are provided for the agent to sanitize, validate, or escape the content received from third-party connectors before processing it.
Audit Metadata