azure-devops
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from Azure DevOps API responses via the Apideck Proxy service. This creates a potential surface for indirect prompt injection attacks where malicious instructions hidden in the API data could attempt to override agent behavior.
- Ingestion points: External data returned from Azure DevOps API endpoints through the proxy at
https://unify.apideck.com/proxy(SKILL.md). - Boundary markers: Absent. The instructions do not specify delimiters or provide warnings to the agent to ignore potentially malicious instructions embedded in the API response.
- Capability inventory: The skill provides the agent with the configuration and logic necessary to perform network requests to external endpoints (SKILL.md).
- Sanitization: No sanitization, validation, or filtering steps are described for the content received from the downstream Azure DevOps API before it is processed by the agent.
Audit Metadata