machine-learning-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for mapping and implementing ML data pipelines, which inherently process untrusted external inputs.
- Ingestion points: Training artifacts, feature generation flows, and model inference outputs from the production environment.
- Boundary markers: The instructions lack specific delimiters or warnings to ignore embedded instructions within the data being processed.
- Capability inventory: The skill utilizes workspace-write permissions to modify pipeline and integration code, which could be exploited if malicious instructions are ingested.
- Sanitization: No explicit requirements for data sanitization or verification are provided to mitigate the risk of processing attacker-controlled content.
Audit Metadata