ml-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is a set of guidelines and instructions for acting as an ML engineer. No patterns associated with prompt injection, credential theft, or unauthorized network operations were found.
- [NO_CODE]: This skill package contains only markdown documentation. There are no executable scripts, binaries, or configuration files that would perform operations on the host system.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions include a reference to an external implementation playbook, which represents a potential ingestion surface for untrusted data.
- Ingestion points: Instruction to open
resources/implementation-playbook.md(SKILL.md). - Boundary markers: None identified; no specific delimiters are defined to separate the agent's instructions from the playbook content.
- Capability inventory: No scripts or tool execution logic are included in the skill body.
- Sanitization: No validation or sanitization instructions are provided for the content within the referenced file.
Audit Metadata