verifying-markdown-formatting
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external Markdown files, which introduces a surface for indirect prompt injection where malicious instructions could be embedded in document content.\n- Ingestion points: Target Markdown file ingested in step 1 of the Workflow.\n- Boundary markers: The skill lacks explicit boundary markers or instructions for the agent to ignore commands embedded within the target file.\n- Capability inventory: Includes file reading and writing for formatting checks and fixes; no network or code execution capabilities were detected.\n- Sanitization: No sanitization or content validation is performed on the ingested Markdown data.
Audit Metadata