marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read context from files such as .agents/product-marketing.md or .claude/product-marketing.md. This ingestion of external data represents a surface for indirect prompt injection, where malicious instructions inside those files could influence agent behavior. However, because this skill does not include capabilities for network access, file modification, or command execution, the security impact is negligible.
- Evidence: 1. Ingestion points: SKILL.md instructions for reading product-marketing context files. 2. Boundary markers: Absent. 3. Capability inventory: Only text generation and advice; no tools for shell access, network requests, or file writes are present. 4. Sanitization: Absent.
Audit Metadata