markdown-doc
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and provides templates for text generation. It does not attempt to execute commands, access sensitive files, or perform network exfiltration. The curl and npm commands found in the file are part of documentation templates intended for the user, not for agent execution.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface for indirect prompt injection because it processes external data such as project descriptions and existing user documents.
- Ingestion points: Project descriptions, feature lists, and existing documentation provided by the user (SKILL.md, Step 1).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded instructions in the ingested data.
- Capability inventory: No dangerous tools (shell access, file writing, or network operations) are enabled for this skill; its output is limited to text generation.
- Sanitization: No specific sanitization or filtering logic is defined for the input data.
Audit Metadata