signals-scout-surveys
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 open-text feedback from survey respondents, which presents a surface for potential indirect prompt injection.
- Ingestion points: Survey responses are ingested via
execute-sqlcalls to theeventstable as outlined inSKILL.mdandreferences/response-querying.md. - Boundary markers: The skill lacks explicit data delimiters but enforces logic-based boundaries by requiring convergence from multiple distinct respondents (at least 5, or 3 if correlated with activity logs) before a theme is considered report-worthy.
- Capability inventory: The agent is authorized to use
emit_reportandedit_reportto send data to the project inbox, andscout-scratchpad-rememberto persist data between runs. - Sanitization: The instructions explicitly require the agent to strip personally identifiable information (PII) from responses and truncate verbatim quotes to the sentence level.
Audit Metadata