signals-scout-error-tracking
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from error reports, which could be leveraged to perform indirect prompt injection attacks.
- Ingestion points: The agent reads external and potentially attacker-controlled data from stack traces, issue descriptions, and activity logs via tools like
query-error-tracking-issue,execute-sql(against the events table), andadvanced-activity-logs-list. - Boundary markers: The instructions do not define clear delimiters or provide the agent with specific 'ignore' warnings for instructions that might be embedded within the error data or logs it processes.
- Capability inventory: The skill has significant capabilities including writing to the report channel (
emit_report,edit_report) and persisting data across sessions via the scratchpad (scout-scratchpad-remember). - Sanitization: There is no mention of sanitizing or filtering the content extracted from error stack traces or logs before the agent processes or reports on it.
Audit Metadata