review-site-intent-leads
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a command to install a Model Context Protocol (MCP) server:
claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user. This modifies the agent's runtime environment by adding external tools. - [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch functionality and configuration from the vendor-owned endpoint
https://mcp.manypi.com/mcp. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and analyzing data from third-party review platforms, which creates an indirect prompt injection surface.
- Ingestion points: External review platforms (e.g., G2, Capterra) and comparison pages as specified in SKILL.md.
- Boundary markers: No explicit boundary markers or delimiters for untrusted content are defined in the instructions.
- Capability inventory: The toolset includes monitoring remote reviews and researching specific reviewer details to generate leads.
- Sanitization: The skill does not mention or implement sanitization or validation of the ingested review content.
Audit Metadata