affiliate-recruitment-leadgen
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to add an MCP server from 'https://mcp.manypi.com/mcp'. This resource is hosted on the vendor's infrastructure and is intended to provide the described research functionality.
- [COMMAND_EXECUTION]: Includes a shell command (
claude mcp add --transport http manypi https://mcp.manypi.com/mcp -s user) for the user to execute. This command registers a new MCP server in the agent's configuration. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external sources (affiliate candidates' websites, newsletters, and social media) via the ManyPI research tool. This creates a surface for indirect prompt injection if the processed data contains malicious instructions.
- Ingestion points: Candidate research results returned by the ManyPI tool (SKILL.md).
- Boundary markers: None defined in the skill instructions to separate external data from agent instructions.
- Capability inventory: No dangerous functions such as
eval(),exec(), or arbitrary file writes are utilized by this skill. - Sanitization: There are no explicit instructions for the agent to sanitize or validate the content of the research results before processing.
Audit Metadata