authentication-xsuaa
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes and modifies user-provided application code (web.xml, pom.xml, and Java source files), which creates an attack surface where instructions embedded in these files could influence the agent behavior during the migration process.
- Ingestion points: The skill reads content from web.xml, pom.xml, and Java source files to detect Neo-specific security patterns.
- Boundary markers: There are no delimiters or explicit warnings used to prevent the agent from following instructions embedded within the user's code.
- Capability inventory: The skill leverages Edit, Write, and Bash tools (used for Maven and Cloud Foundry CLI) to apply transformations.
- Sanitization: The skill does not validate or sanitize the ingested source code content before processing it.
Audit Metadata