performance-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external telemetry data, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill's primary function involves collecting and analyzing traces, profiles, and logs from external observability platforms (e.g., Datadog, New Relic, OpenTelemetry) as specified in the 'Instructions' and 'Capabilities' sections.
- Boundary markers: The skill does not provide any instructions for using delimiters or boundary markers to help the agent distinguish between its own system instructions and instructions possibly embedded within the ingested logs or traces.
- Capability inventory: The skill enables a wide range of capabilities including execution of load testing tools (k6, JMeter, Artillery), API testing, and cloud infrastructure profiling, which could be abused if malicious instructions are processed.
- Sanitization: There is no evidence of sanitization, filtering, or validation logic meant to sanitize external data before it is interpreted by the agent.
Audit Metadata