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 potentially untrusted data from error logs and stack traces, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Exception data retrieved via
query-error-tracking-issues-list,query-error-tracking-issue, andexecute-sqlqueries against theeventstable as described inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters (e.g., XML tags or triple quotes) or "ignore embedded instructions" warnings for the data being analyzed.
- Capability inventory: The skill has access to reporting tools (
emit_report,edit_report) and persistent memory through the scratchpad (scout-scratchpad-remember), allowing it to escalate findings and store state across runs. - Sanitization: There is no mention of sanitizing, escaping, or validating the content of stack traces or error messages before they are processed by the agent.
Audit Metadata