offsite-signal-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill includes explicit instructions to maintain security boundaries, such as requiring user authorization for all external side effects, spend changes, and persistent data writes.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted external data, including scraped web content and third-party exports. However, it contains specific defensive instructions for the agent to treat such content as evidence only and to disregard any instructions that may be embedded within that data, effectively mitigating the risk of indirect prompt injection.
- [DATA_EXPOSURE]: The documentation references integrations with various third-party platforms (e.g., Google Search Console, HubSpot, Salesforce). It provides clear guidance on secure data handling, specifically advising that API keys must be kept out of skill files and source control, and ensuring that imported evidence includes provenance tracking.
Audit Metadata