community-marketing
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were found. The skill serves purely as a knowledge base and prompt template for community building.
- [NO_CODE]: This skill is composed entirely of Markdown documentation and YAML metadata. It does not include any Python scripts, Node.js packages, shell commands, or binary executables, significantly reducing the attack surface.
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions to read context from external local files (
.agents/product-marketing-context.md). - Ingestion points: Files located at
.agents/product-marketing-context.mdor.claude/product-marketing-context.md. - Boundary markers: None defined; the agent is simply instructed to read the file.
- Capability inventory: None; the skill does not define any tools, network access, or file-system writing capabilities.
- Sanitization: None; the instructions assume the provided context file is trusted.
Audit Metadata