The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes dynamic context injection (!command syntax) in SKILL.md to execute shell commands at load time.
One command uses node to parse package.json for specific dependencies related to the Capacitor ecosystem and various billing/analytics SDKs (e.g., Stripe, RevenueCat, PostHog).
Another command uses find to map out relevant configuration files and native directories.
[DATA_EXFILTRATION]: No network exfiltration or credential harvesting patterns were detected. The data collected by the dynamic context commands remains within the local execution environment for the agent's use.
[PROMPT_INJECTION]: The instructions are instructional and safe. No attempts to bypass safety filters or override system behavior were found.
[REMOTE_CODE_EXECUTION]: No patterns of downloading or executing remote code from external sources were identified.

subscription-app-revenue