enterprise-tomcat-web
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external Tomcat
web.xmlfiles, which acts as a vector for indirect instructions embedded within configuration data. - Ingestion points: The skill reads local file content using
daselcommands as defined inSKILL.md. - Boundary markers: The instructions do not define delimiters or provide specific warnings to the agent to treat the XML content as untrusted data.
- Capability inventory: The skill performs shell command execution using the
daselutility for data extraction. - Sanitization: No sanitization or validation is applied to the data extracted from the XML deployment descriptors before it is processed by the agent.
Audit Metadata