signals-scout-revenue-analytics
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses PostHog platform tools (e.g.,
execute-sql,external-data-sources-list) to perform read-only monitoring of revenue analytics tables and synchronization status within a secured sandbox environment. - [SAFE]: No obfuscation, data exfiltration, or unauthorized privilege escalation patterns were identified. The skill's behavior is consistent with its intended diagnostic purpose for the PostHog agent fleet.
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface: The skill ingests data from external logs and shared memory which may contain instructions from untrusted sources.
- Ingestion points: Data retrieved from
external-data-sync-logsandsignals-scout-scratchpad-search. - Boundary markers: None identified.
- Capability inventory: The agent can perform
signals-scout-emit-signalandsignals-scout-scratchpad-remember. - Sanitization: Logs and memory entries are processed without explicit validation of embedded instructions.
Audit Metadata