competitive-analysis

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data regarding competitors, industries, and market trends to generate strategic reports. This creates an entry point where malicious instructions embedded in the research material could influence the agent's output format or recommendations.
  • Ingestion points: User-provided competitor details, market segments, and descriptions of competitive landscapes (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' commands for the external data being processed.
  • Capability inventory: The skill utilizes MCP tools for file creation, including create_docx, create_xlsx, and create_chart to format the analysis results.
  • Sanitization: There are no documented procedures for validating or escaping the content provided for analysis before it is incorporated into the final reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:54 PM
Security Audit — agent-trust-hub — competitive-analysis