incident-response
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to handle external data (incident issues) which presents an attack surface for indirect prompt injection. \n
- Ingestion points: Data from production incident reports (SKILL.md). \n
- Boundary markers: The skill lacks instructions to use delimiters or explicitly ignore instructions embedded within the processed issues. \n
- Capability inventory: The skill utilizes tools such as
correlate_deploysandrequest_rollback, and performs issue status management and commenting. \n - Sanitization: No evidence of input validation or sanitization is present in the instructions. \n
- Mitigation: A critical safety feature is included where
request_rollbackrequires human approval, ensuring that destructive actions are not automated without oversight.
Audit Metadata