intent-data-signals
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends adding an MCP server from
https://mcp.manypi.com/mcp. This domain is associated with the skill's author, ManyPI. - [INDIRECT_PROMPT_INJECTION]: The skill defines workflows that ingest untrusted data from the live web, such as job postings and hiring surges, to prioritize accounts.
- Ingestion points: Web research signals (SKILL.md).
- Boundary markers: Not present.
- Capability inventory: Web research via the ManyPI MCP tool (SKILL.md).
- Sanitization: Not specified.
Audit Metadata