nebula-logger-plugin-development
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documentation describes a plugin framework designed to ingest and process log data, which constitutes an attack surface for indirect prompt injection.
- Ingestion points: Data enters the plugin context via the
LoggerTriggerableContextandLoggerBatchableContextinterfaces described inSKILL.md, which provide access to records likeLogEntryEvent__eandLog__c. - Boundary markers: The provided code templates and instructions do not include boundary markers or delimiters to separate log content from instructional prompts.
- Capability inventory: As detailed in
SKILL.md, plugins have the capability to perform DML (archiving logs), publish events, and execute outbound integrations (e.g., Slack notifications). - Sanitization: There are no explicit instructions or requirements provided for sanitizing or validating the log data before processing or exfiltrating it to external services.
Audit Metadata