mpm-orchestration-demo
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill demonstrates patterns for ingesting untrusted user input ($ARGUMENTS) which is then passed to subsequent agents and skills, creating a potential surface for indirect prompt injection.
- Ingestion points: User-supplied arguments within the command templates defined in SKILL.md.
- Boundary markers: The documentation recommends the use of structured data contracts (e.g., using explicit RESULT and ISSUE markers) to establish clear boundaries and reduce ambiguity in agent communication.
- Capability inventory: The templates describe workflows utilizing the Agent and Skill tools, which include capabilities for file system operations such as writing review reports.
- Sanitization: The skill contains explicit instructions for defensive design, requiring that downstream skills validate the presence and format of data in the context before execution.
- [NO_CODE]: The skill consists entirely of markdown documentation and reference templates, containing no executable scripts, binaries, or active code components.
Audit Metadata