skills/sap-samples/html5-applications-migration-skills-for-sap-btp/appfront-validate/Gen Agent Trust Hub
appfront-validate
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFECREDENTIALS_UNSAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill prompts for and handles user credentials, including SAP BTP Application Frontend API passwords and application login passwords. It uses secure input methods (read -s) and includes instructions for the agent to avoid logging or storing these passwords.
- [COMMAND_EXECUTION]: The skill uses shell commands (find, grep) and the afctl CLI tool to discover project structure and perform authentication tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from multiple sources, establishing an attack surface for indirect prompt injection.
- Ingestion points: Local project files (mta.yaml, xs-app.json, xs-security.json, manifest.json) and remote content fetched via Playwright (index.html, manifest.json, and runtime xs-app.json).
- Boundary markers: The instructions do not utilize specific delimiters or explicit warnings to ignore instructions embedded within the ingested data.
- Capability inventory: The skill possesses capabilities to execute shell commands (bash, afctl), perform network requests (WebFetch), and interact with browsers via Playwright tools.
- Sanitization: There is no evidence of explicit sanitization, filtering, or escaping of the ingested content prior to processing by the agent.
Audit Metadata