lead-intelligence
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection.
- Ingestion points: External data is fetched in enrichment-agent.md and signal-scorer.md from X tweets, bios, and web search results.
- Boundary markers: The instructions do not specify the use of delimiters or warnings when interpolating external content into outreach drafts in outreach-drafter.md.
- Capability inventory: The skill has access to Bash, social media write APIs, and local mail drafting tools.
- Sanitization: No specific content filtering or sanitization of external data is defined to prevent instructions embedded in lead data from influencing output.
- [COMMAND_EXECUTION]: Several sub-agents, including signal-scorer.md, mutual-mapper.md, and enrichment-agent.md, are configured to use the Bash tool to facilitate data handling and search operations.
Audit Metadata