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, andexecute-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-sqland write capabilities viascout-emit-report,scout-edit-report, andscout-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