marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill ingests data from local files which could contain malicious instructions designed to influence the agent's behavior.\n
- Ingestion points:
.claude/product-marketing-context.mdandreferences/ideas-by-category.md.\n - Boundary markers: Absent. There are no delimiters used to separate user/file data from system instructions.\n
- Capability inventory: Limited to internal reasoning and text generation. The skill possesses no capabilities for command execution (subprocess), network exfiltration, or file modification.\n
- Sanitization: Absent. Content from ingested files is used directly to inform the agent's recommendations.
Audit Metadata