proposal-writer

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted user input (solution details, pricing, client info) and process it into structured documents via MCP tools, creating a standard surface for indirect injection.
  • Ingestion points: User-supplied opportunity details, solution descriptions, and project requirements as described in the 'How to Use' section of SKILL.md.
  • Boundary markers: Absent. The provided templates interpolate user input directly into Markdown and document structures without explicit delimiters or warnings to ignore embedded instructions.
  • Capability inventory: The skill is configured to use the create_docx, fill_docx_template, and create_pptx tools from the office-mcp server, allowing it to write to the local filesystem.
  • Sanitization: Absent. The skill instructions do not specify any validation, filtering, or escaping of user-provided content before it is processed by the file-writing tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:46 AM
Security Audit — agent-trust-hub — proposal-writer