signals-scout-ai-observability

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from LLM traces and evaluation results, which presents a surface for potential indirect prompt injection attacks.
  • Ingestion points: Untrusted data enters the agent context through query-llm-trace, execute-sql (reading $ai_generation, $ai_trace, and $ai_evaluation events), and scout-scratchpad-search as described in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands when processing the content of LLM traces or generation events.
  • Capability inventory: The agent has the capability to write to a durable scratchpad via scout-scratchpad-remember and to author or edit inbox reports through scout-emit-report and scout-edit-report.
  • Sanitization: There is no evidence of specific sanitization, filtering, or validation logic applied to trace content before it is included in reports or stored in the agent's memory.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 01:03 AM
Security Audit — agent-trust-hub — signals-scout-ai-observability