trade-and-dealer-enablement
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read various local files for context, establishing a surface for indirect prompt injection.\n
- Ingestion points: Reads from .agents/marketing-strategy.md, .agents/marketing-learnings.md, .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md (referenced in SKILL.md).\n
- Boundary markers: There are no instructions specifying the use of delimiters or warnings to treat ingested content as untrusted.\n
- Capability inventory: Analysis of all instructions and metadata confirms no capabilities for network operations, file system modifications, or shell command execution.\n
- Sanitization: The skill does not implement validation or sanitization of the content retrieved from external files.
Audit Metadata