pw-pair-programming
Fail
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: HIGHCREDENTIALS_UNSAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
- [CREDENTIALS_UNSAFE] (HIGH): The file
scripts/pp/download.nucontains logic to programmatically extract the user's ChatGPT session token. It executes JavaScript viapw evalto call/api/auth/sessionand retrieve theaccessToken. This token is then stored in a variable and used for subsequent authenticated API requests. - Evidence:
let token_js = "(() => { const xhr = new XMLHttpRequest(); xhr.open('GET', '/api/auth/session', false); ... return { token: session.accessToken }; })()"inscripts/pp/download.nu. - [DATA_EXFILTRATION] (HIGH): The skill is designed to read arbitrary files from the local filesystem and transmit them to a remote browser session.
scripts/pp/attachments.nuencodes local files into Base64 and injects them into the browser's DOM, whilescripts/pp/compose.nureads file contents into prompt strings. - Evidence:
let bytes = (open --raw $file_path | into binary)andbase64: ($bytes | encode base64 ...)inscripts/pp/attachments.nu. - [COMMAND_EXECUTION] (MEDIUM): The skill relies heavily on
pw evalandpw eval-jsto execute arbitrary JavaScript within the context of the automated browser. This allows the skill to manipulate the browser session, extract data, and trigger UI actions like clicking buttons. - Evidence: Extensive use of
pw evalacrossattachments.nu,download.nu,messaging.nu, andsession.nu. - [REMOTE_CODE_EXECUTION] (MEDIUM): The skill downloads content from the remote assistant via
scripts/pp/download.nu. If an attacker-controlled assistant provides a malicious file that the user is then prompted to execute (a common pattern in pair-programming workflows), it leads to RCE. - Evidence:
let download_result = (pw eval-js $download_js)and subsequent file saving logic inscripts/pp/download.nu. - [PROMPT_INJECTION] (LOW): The skill facilitates indirect prompt injection by reading local source code and assistant responses into the agent's context. If these files contain hidden instructions, they could manipulate the behavior of the 'driver' or 'navigator' roles.
- Ingestion points:
pp brief,pp compose, andpp get-response. - Capability inventory: File system read/write, browser automation, network requests via browser.
Recommendations
- AI detected serious security threats
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata