signals-scout-error-tracking
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of exception events, stack traces, and activity logs which could contain attacker-controlled strings. If an attacker can trigger specific error messages, they might influence the content or formatting of the reports generated by this scout.
- Ingestion points: Untrusted data enters the context via
query-error-tracking-issue,execute-sql(querying theeventstable), andadvanced-activity-logs-list. - Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from obeying instructions embedded within the exception data.
- Capability inventory: The skill has the ability to write to external channels using the
emit_reportandedit_reporttools, and manages state across runs using thescout-scratchpad-remembertool. - Sanitization: There is no mention of sanitization, filtering, or escaping logic applied to the exception data before it is interpolated into report fields or the scratchpad.
Audit Metadata