triton-inference-config
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing user-supplied configuration data while having access to broad system interaction tools.
- Ingestion points: User requests containing "triton inference config" patterns and associated machine learning deployment data (SKILL.md).
- Boundary markers: Absent. The skill does not provide delimiters or instructions for the agent to ignore potentially malicious directives embedded in the configuration data.
- Capability inventory: The skill is allowed to use powerful tools including Bash (with arbitrary command execution), Read, Write, and Edit (SKILL.md).
- Sanitization: No input validation, escaping, or filtering routines are defined for the data processed by the skill.
Audit Metadata