observability-engineer
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 telemetry data which serves as an untrusted ingestion point for potentially malicious instructions.
- Ingestion points: The skill is designed to ingest and analyze metrics, logs, and distributed traces from various sources (referenced in the 'Capabilities' section of
SKILL.md). - Capability inventory: The skill has broad capabilities to generate and manage infrastructure, including 'Terraform modules', 'Ansible playbooks', 'GitOps workflows', and 'Automated incident response' (referenced in
SKILL.md). - Boundary markers: There are no explicit instructions to use delimiters or 'ignore' instructions when processing external telemetry data to prevent the agent from obeying embedded malicious commands.
- Sanitization: While the 'Safety' section correctly identifies exfiltration risks (logging credentials), it lacks specific sanitization or validation requirements for external content before it is used in code generation or system commands.
Audit Metadata