export-chat-history

Warn

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: MEDIUMDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill reads sensitive local data from directories used by Claude Code and Cursor to store chat history and project context.
  • Evidence: Scans ~/.claude/projects and ~/.cursor/projects to extract session transcripts and metadata.
  • [DATA_EXFILTRATION]: Aggregated session data is uploaded to a remote service via the GitHub CLI.
  • Evidence: Executes the gh gist create command to publish processed session files.
  • [COMMAND_EXECUTION]: Shell commands are constructed using variables derived from local directory names and file paths.
  • Evidence: Interpolates {project-dir} and $SESSION_FILE within commands like jq, gawk, and stat.
  • [PROMPT_INJECTION]: The skill ingests untrusted chat logs to generate titles and descriptions, creating an indirect prompt injection surface.
  • Ingestion points: Local session logs in ~/.claude/projects/ and ~/.cursor/projects/.
  • Boundary markers: Absent.
  • Capability inventory: File system access, shell execution, and network operations (GitHub CLI).
  • Sanitization: Absent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 21, 2026, 11:15 AM
Security Audit — agent-trust-hub — export-chat-history