needs-analysis
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists exclusively of markdown instructions and prompt templates designed to guide an AI agent through an instructional design process. No malicious patterns were identified.
- [PROMPT_INJECTION]: The instructions do not contain attempts to override agent safety protocols, bypass filters, or extract system prompts. Standard role-playing instructions ('You are an expert instructional designer') are used legitimately for task framing.
- [EXTERNAL_DOWNLOADS]: The skill does not reference or attempt to download any external scripts, packages, or files.
- [COMMAND_EXECUTION]: There are no shell commands, subprocess calls, or dynamic execution patterns present in the documentation or instructions.
- [DATA_EXFILTRATION]: The skill does not perform any network operations or access sensitive system paths (e.g., .ssh, .aws, .env).
- [DATA_INGESTION]: While the skill invites users to paste raw materials like SME transcripts (Category 8 surface), the agent lacks the capabilities (tools, code execution, or network access) to perform any harmful actions if the pasted content contained malicious instructions.
Audit Metadata