platonic-impl-guide
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process external RFC documents to generate implementation designs, which creates a surface for indirect prompt injection. \n
- Ingestion points: The skill reads external specifications from paths like specs/RFC-NNNN.md. \n
- Boundary markers: No explicit delimiters or instructions are provided to the agent to isolate RFC content from system instructions. \n
- Capability inventory: The skill's operations are limited to markdown document generation and do not involve network access, subprocess execution, or sensitive file system operations. \n
- Sanitization: There is no evidence of sanitization or validation of the input RFC content before it is processed by the agent. \n- [NO_CODE]: The skill does not include any executable scripts, binaries, or dependencies. It is composed entirely of Markdown instructions, reference guides, and templates for manual or agent-assisted documentation tasks.
Audit Metadata