sap-ai-core

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using the btp CLI for infrastructure provisioning and curl for managing AI Core resources and retrieving authentication tokens.
  • [CREDENTIALS_UNSAFE]: The workflow involves extracting sensitive OAuth2 credentials (Client ID and Client Secret) from service bindings and storing them in environment variables for API authentication.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes an ingestion surface where the agent processes external data from service binding files and API responses to determine deployment statuses and available models.
  • Ingestion points: Processes JSON output from the btp CLI and SAP AI Core API responses via jq and curl (e.g., ai-core-key.json).
  • Boundary markers: None explicitly defined for the ingested data.
  • Capability inventory: Shell command execution (btp, curl, jq) and execution of local preflight scripts (scripts/region-preflight/region-preflight.sh).
  • Sanitization: Relies on structural parsing using jq to extract specific fields from the JSON data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 11:53 PM
Security Audit — agent-trust-hub — sap-ai-core