build-clusters
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, such as seed topics and existing website content, which could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: The 'Before You Start' section requires the agent to gather 'Seed topic' and 'Existing content' from the user or external sources.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore or sanitize embedded instructions within the processed data.
- Capability inventory: The skill itself consists of markdown instructions and does not contain scripts or commands for file system modification, network exfiltration, or dynamic code execution.
- Sanitization: The instructions do not include steps for validating or escaping the external content before it is used in the clustering process.
Audit Metadata