lead-scoring
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run a directory listing command (
ls) to verify the installation status of recommended companion skills in local directories such as~/.claude/skills/. - [EXTERNAL_DOWNLOADS]: The skill recommends installing additional companion tools from the AbsolutelySkilled repository via the npx package manager.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection via user-provided lead data. 1. Ingestion points: Lead and company firmographic and behavioral data provided by the user. 2. Boundary markers: No delimiters are present to separate external content from instructions. 3. Capability inventory: Local directory listing and tool installation suggestions. 4. Sanitization: No data sanitization is specified for ingested lead data.
Audit Metadata