signals-scout-feature-flags
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the execute-sql tool to perform analytical queries on PostHog events and system tables. This activity is strictly limited to the skill's primary function of detecting traffic contradictions and flag debt.
- [PROMPT_INJECTION]: The skill handles untrusted data from event properties like flag keys and responses. It contains specific instructions to sanitize and truncate these inputs to prevent potential indirect prompt injection, treating them as data for reporting rather than executable instructions.
Audit Metadata