competitor-traffic-leadgen
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides a command to install an external MCP server:
claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user. This URL is owned by the skill vendor, manypicom. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources, which presents an attack surface for indirect prompt injection.
- Ingestion points: The skill instructions describe monitoring and analyzing external content such as "Public complaints about a competitor on social media," "review-site activity," and "Job postings" via the ManyPI MCP tool.
- Boundary markers: The provided instructions do not specify explicit boundary markers or delimiters to separate untrusted external data from agent instructions.
- Capability inventory: The skill uses the
claude mcp addcommand to integrate the ManyPI tool, which performs the external data retrieval and analysis. - Sanitization: There are no explicit mentions of sanitization or validation steps for the data retrieved from external review sites or social media platforms.
Audit Metadata