signals-scout-web-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted web traffic data, including URLs, referrers, and UTM values, which are potential vectors for indirect prompt injection or referrer spam attacks.
- Ingestion points: Data is ingested from the
sessionsandeventstables via theexecute-sqltool. - Boundary markers: The skill contains a dedicated 'Untrusted data' section instructing the agent to treat these inputs strictly as data, not instructions.
- Capability inventory: The agent can execute SQL queries, store data in a persistent scratchpad, and author/edit reports in a dedicated inbox.
- Sanitization: The instructions explicitly require the agent to truncate user-supplied strings, slugify identifiers for internal memory, and perform provenance checks (e.g., session duration and pageview distributions) to identify and ignore spam traffic.
Audit Metadata