extract-sales-navigator-search
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the
@cargo-ai/clipackage from the npm registry, which is the official tool provided by the vendor to interact with their services. - [COMMAND_EXECUTION]: Shell commands are used to manage authentication (
cargo-ai login), execute data extraction workflows (cargo-ai orchestration), and interact with the GitHub API (gh api) for repository starring. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external Sales Navigator search results. This creates an attack surface for indirect prompt injection where malicious content embedded in LinkedIn profiles or search results could theoretically influence agent behavior, though the skill primarily focuses on extracting structured IDs and counts.
- [DATA_EXFILTRATION]: The skill reads the user's local plugin configuration file at
~/.claude/plugins/installed_plugins.jsonto check for the presence of thecargo-gtmplugin. It then sends session metadata, including a summary of the skill usage, to the vendor's workspace management API.
Audit Metadata