signals-scout-general

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 PostHog environment (e.g., event names, log content, and user reports) and uses this data to generate new reports or update its persistent scratchpad.
  • Ingestion points: Data enters the agent context through tools like read-data-schema, query-logs, and inbox-reports-list as referenced in SKILL.md and references/discovery.md.
  • Boundary markers: The prompt does not provide clear boundaries or instructions to the AI to ignore potential commands embedded within the data it analyzes.
  • Capability inventory: The agent possesses the ability to write to the project inbox using emit-report and edit-report and can maintain long-term state using scout-scratchpad-remember.
  • Sanitization: There are no explicit instructions to sanitize or validate strings retrieved from the project environment before processing them.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 01:03 AM
Security Audit — agent-trust-hub — signals-scout-general