lead-lists
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process data retrieved from external sources, specifically public profile pages and email search results via the
outreachcommand-line tool. - Ingestion points: Data enters the agent's context through the output of
outreach people role,outreach people find, andoutreach email listcommands, which fetch information from public profiles. - Boundary markers: The skill does not provide specific instructions or delimiters to help the agent distinguish between data and potential instructions embedded within the fetched profile content.
- Capability inventory: The skill utilizes the
bashtool for command execution and themail draftfunctionality to write content to connected email accounts (Gmail/Outlook). - Sanitization: There are no explicit sanitization or filtering steps described for the external content before it is processed or used in email drafts.
- [COMMAND_EXECUTION]: The skill relies on executing various CLI commands (
outreach,jq,mail) within a shell environment provided by thehedwigaiMCP. It performs tasks such as market research, contact expansion, and email verification through these commands. - [EXTERNAL_DOWNLOADS]: The documentation directs users to install external plugins (
un-seen/hedwigai-skills) from a marketplace and connect to a remote MCP server located atmcp.hedwigai.com. These resources are owned by the skill's vendor.
Audit Metadata