wrap-history

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes several shell commands (find, stat, jq, split) and a provided bash script (extract-session.sh) to locate, parse, and handle large session history files stored in the user's home directory.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes historical conversation data which could contain malicious instructions designed to influence the agent's behavior during the analysis phase.
  • Ingestion points: Historical session logs located at ~/.claude/projects/*.jsonl.
  • Boundary markers: Absent. The skill does not use delimiters or explicit instructions to treat the ingested history as data rather than instructions.
  • Capability inventory: The skill can execute shell commands and spawn subagents (Task), providing a path for injected instructions to trigger actions.
  • Sanitization: Absent. No filtering or sanitization of the extracted message content is performed beyond structural extraction with jq.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 06:07 AM