prompt-history

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the pmtx CLI tool and the gh (GitHub) CLI to extract logs, curate content, and post comments to pull requests.
  • [EXTERNAL_DOWNLOADS]: Directs users to install the pmtx binary from the author's GitHub repository (github.com/gutierrezje/promptex) using cargo install.
  • [PROMPT_INJECTION]: Includes comprehensive defensive instructions specifically designed to prevent the agent from following malicious commands (e.g., 'Ignore previous instructions') that might be embedded in the log data being processed. This is a robust mitigation against indirect prompt injection.
  • [DATA_EXFILTRATION]: Enforces a strict security policy requiring the redaction of API keys, tokens, and other sensitive environment variables from logs before any output is generated or shared.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 04:37 AM