content-demand-finder
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection as it processes untrusted data. 1. Ingestion points: User-provided website domains, business descriptions, and customer market data via the $ARGUMENTS variable. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic. 3. Capability inventory: The skill is instructional and limited to text generation; it suggests optional transitions to the keyword-research and content-brief tools. It lacks direct file system write access, shell execution permissions, or network exfiltration capabilities. 4. Sanitization: No sanitization is performed on input as the skill relies on model reasoning for output generation. The overall risk is contained due to the lack of exploitable capabilities.
- [EXTERNAL_DOWNLOADS]: The skill documentation references a connector URL on the official Claude.ai domain and an MCP endpoint (ubersuggest-mcp.neilpatelapi.com) belonging to the vendor. These references are used for standard service integration and are documented neutrally as legitimate configuration steps for the Ubersuggest platform.
Audit Metadata