schema

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and incorporate context from local project files such as .agents/product-marketing.md or .claude/product-marketing.md. This ingestion point creates a surface for indirect prompt injection, as an attacker who can modify these files could embed instructions to influence the agent's behavior. While the skill's capabilities are primarily restricted to generating structured data (JSON-LD), the instructions lack explicit boundary markers or input sanitization for the content of these context files. (Evidence: SKILL.md under 'Initial Assessment').
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 09:20 PM