import-linkedin-history
Warn
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bash(unzip *)tool to extract user-provided ZIP files. Executing shell commands on external archives poses a risk of command injection or path traversal (Zip Slip) if the archive contents or the provided file path contain malicious characters or structural anomalies. - [DATA_EXFILTRATION]: The skill is designed to handle highly sensitive Personal Identifiable Information (PII), including private message history, connection lists, and profile data. While the processing is described as local, the access to this data constitutes a significant exposure risk within the agent's context.
- [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8).
- Ingestion points: Reads external CSV and Markdown files extracted from a LinkedIn data export ZIP.
- Boundary markers: No delimiters or instructions are used to separate untrusted data from agent instructions.
- Capability inventory: The skill has access to
Read,Write, and severalBashutility commands. - Sanitization: There is no evidence of content sanitization or validation for the data processed from the export files.
Audit Metadata