marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data from specific project files to provide context-aware marketing advice. While this represents a standard functional pattern for AI agents, it creates an attack surface where malicious content in those files could attempt to influence agent behavior.
- Ingestion points:
SKILL.mdinstructs the agent to read.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.mdif they exist. - Boundary markers: Absent. The skill does not provide specific instructions to the agent to treat this data as untrusted or to use delimiters.
- Capability inventory: The skill does not define any
allowed-toolsor scripts that perform network operations, file writes, or command execution, limiting the risk of exploitation. - Sanitization: Absent. There is no instruction to validate or sanitize the content of the marketing context files.
Audit Metadata