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
pmtxCLI tool and thegh(GitHub) CLI to extract logs, curate content, and post comments to pull requests. - [EXTERNAL_DOWNLOADS]: Directs users to install the
pmtxbinary from the author's GitHub repository (github.com/gutierrezje/promptex) usingcargo 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