The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands like git add, git commit, and git push to automate the deployment of code changes to the production branch across several repositories.
[DATA_EXFILTRATION]: The skill reads sensitive local files including subscriptionUtils.ts, StripeService.ts, and .env.example using absolute paths, which may expose internal configuration and business logic.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of external data. Ingestion points: Data is pulled from the Stripe API and various local source and documentation files. Boundary markers: There are no markers to isolate ingested data from agent instructions. Capability inventory: The agent has permissions to write to the file system, interact with the Stripe API, and execute shell commands. Sanitization: The skill lacks sanitization or validation of the data retrieved from external sources before processing it.

price-change