detect-prod-regressions
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and processing untrusted data from external observability platforms.
- Ingestion points: The skill retrieves error messages, stack traces, and log data from Datadog environments (
prod-us,prod-eu,prod-hipaa,prod-jp) as defined inSKILL.md. - Boundary markers: No explicit boundary markers or delimiters are defined to separate the ingested log content from the agent's core instructions.
- Capability inventory: The skill can interact with the
linear-bug-triagetool to create new issues or comment on existing ones based on the analyzed data. - Sanitization: There are no instructions for sanitizing or escaping the error messages or logs before they are included in the findings table or sent to Linear.
Audit Metadata