bullmq
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill uses authoritative directives ("CRITICAL", "MUST", "Do not proceed without") to mandate that the agent performs a network fetch before any other action. This is an attempt to override the agent's standard autonomous reasoning and decision-making process.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and prioritize data from an external source, which could allow malicious instructions in the remote document to influence agent behavior.
- Ingestion points: Mandatory
WebFetchinstruction located inSKILL.md. - Boundary markers: Absent; the skill instructs the agent to prioritize external content over its internal training data without providing delimiters.
- Capability inventory: The skill utilizes the agent's web fetching capabilities to retrieve live documentation.
- Sanitization: Absent; there is no instruction for the agent to validate or filter the content retrieved from the external URL.
- [EXTERNAL_DOWNLOADS]: The skill fetches live documentation from the official BullMQ domain (
docs.bullmq.io).
Audit Metadata