sap-fiori-url-generator
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary logic is restricted to local file reading and string manipulation for URL construction. No malicious behaviors or safety violations were identified.
- [PROMPT_INJECTION]: The skill processes data from a local JSON file (AppList.json) which is then used in the agent's output. Mandatory Evidence Chain: 1. Ingestion points: AppList.json; 2. Boundary markers: Not present in prompts; 3. Capability inventory: No dangerous capabilities such as network access, file writing, or command execution; 4. Sanitization: Access is limited to specific JSON field lookups. While a surface for indirect prompt injection exists, it is not exploitable due to the absence of risky capabilities.
- [REMOTE_CODE_EXECUTION]: A testing script uses dynamic loading to import a local helper script. This is restricted to a static local path within the skill's directory and does not pose a threat of remote code execution.
Audit Metadata