pp-alaska-airlines
Warn
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: MEDIUMCREDENTIALS_UNSAFEDATA_EXFILTRATIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill uses an
auth login --chromecommand to extract Alaska Airlines authentication cookies from the user's Chrome profile via the macOS keychain. - [DATA_EXFILTRATION]: The CLI supports a
--deliver webhook:<url>flag, which enables the agent to send the output of any command (which may include flight itineraries or account balances) to an arbitrary external URL. - [DATA_EXFILTRATION]: The skill includes a feedback mechanism that can be configured to automatically POST local activity logs to a remote server defined by the
ALASKA_AIRLINES_FEEDBACK_ENDPOINTenvironment variable. - [EXTERNAL_DOWNLOADS]: The skill instructions include downloading and installing a CLI binary from the author's official NPM package (
@mvanhorn/printing-press-library) and GitHub repository. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from airline API responses and external travel valuation websites, which is then processed by the agent.
- Ingestion points: Flight search results and loyalty point valuations scraped from
thepointsguy.com(TPG). - Boundary markers: The skill does not specify the use of delimiters to separate external data from the agent's instructions.
- Capability inventory: The skill possesses file writing capabilities, network access, and the ability to execute shell commands via the
alaska-airlines-pp-clitool. - Sanitization: There is no evidence of sanitization or filtering applied to external content before it is processed by the agent.
Audit Metadata