nest-boot-bullmq
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a task processing structure that ingests data from external Redis queues. This creates a potential attack surface where instructions embedded in a job's payload could be interpreted as commands by an agent monitoring the processor output.
- Ingestion points: The
SourceProcessor.processmethod inreferences/usage.mdaccepts aSourceQueueJobobject which contains untrusted external data. - Boundary markers: There are no explicit delimiters or instructions provided to separate task data from agent instructions in the provided snippets.
- Capability inventory: The skill references capabilities such as logging (
Logger.assign), fetching webpages, and extracting text, which could be misused if influenced by a malicious job payload. - Sanitization: No input validation or sanitization routines are implemented for the
job.datafield before it is logged or processed.
Audit Metadata