conversation-history-setup

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a shell script (scripts/index-history.sh) to invoke an internal tool (ch-index-all) for indexing conversation data. This script uses environment variables and relative paths to locate resources within the plugin environment.
  • [PROMPT_INJECTION]: The indexing of historical conversation data from ~/.claude/projects/ creates an indirect prompt injection surface, as the data being processed may contain user-controlled content from previous interactions.
  • Ingestion points: Local conversation logs in ~/.claude/projects/.
  • Boundary markers: None identified in the provided scripts or documentation.
  • Capability inventory: Shell script execution via scripts/index-history.sh.
  • Sanitization: No sanitization is performed by the indexing wrapper script before processing the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 01:24 AM
Security Audit — agent-trust-hub — conversation-history-setup