pp-stripe
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
stripe-pp-clibinary usingnpx -y @mvanhorn/printing-press-library install stripe --cli-onlyorgo install github.com/mvanhorn/printing-press-library/library/payments/stripe/cmd/stripe-pp-cli@latest. These resources are hosted on GitHub and NPM under the author's namespace. - [COMMAND_EXECUTION]: The skill's primary function is to execute shell commands using the
stripe-pp-clibinary to perform Stripe operations and analytics. - [DATA_EXFILTRATION]: The
stripe-pp-clitool includes a--deliver webhook:<url>flag, which allows the agent to POST command results to an external URL. While a feature of the tool, this provides a mechanism for data to be sent out of the local environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes data ingested from the external Stripe API (e.g., customer profiles, metadata, and event logs) and stores it in a local SQLite mirror for analysis.
- Ingestion points: Data is fetched from the Stripe API and the local
resourcestable in the SQLite mirror (SKILL.md). - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands were found for the processing of external Stripe data.
- Capability inventory: The skill uses the
Read Bashtool and the CLI itself can write to files (--deliver file:<path>) and send network POST requests (--deliver webhook:<url>) as described in SKILL.md. - Sanitization: There is no evidence of sanitization or validation of the data retrieved from Stripe before it is processed by the CLI or presented to the agent.
Audit Metadata