signals-scout-experiments

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 the external PostHog environment, which could be exploited by an attacker to influence the agent's behavior via indirect prompt injection.
  • Ingestion points: The agent ingests data from external sources such as experiment metadata (names, descriptions) and event properties via tools like experiment-get, experiment-results-get, and execute-sql.
  • Boundary markers: The instructions lack explicit boundary markers or delimiters to differentiate between system instructions and data retrieved from the environment.
  • Capability inventory: The agent possesses powerful read capabilities through execute-sql and write capabilities via scout-emit-report, scout-edit-report, and scout-scratchpad-remember.
  • Sanitization: There are no instructions for sanitizing, validating, or escaping external data before it is interpolated into the agent's internal reasoning or its final reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 01:03 AM
Security Audit — agent-trust-hub — signals-scout-experiments