re-android-crypto
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and analyzing untrusted external data from Android applications.
- Ingestion points: The skill processes Android application packages (APKs) via static analysis (JADX) and intercepts runtime data from third-party processes via Frida hooks.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat data retrieved from the target application as untrusted or to ignore embedded instructions within that data.
- Capability inventory: The skill utilizes powerful tools including
fridafor dynamic instrumentation,adbfor device interaction, andpython3for script execution. - Sanitization: The instructions do not define sanitization or validation logic for the data extracted from external applications before it is presented to the agent for analysis.
- [DYNAMIC_EXECUTION]: The skill employs dynamic instrumentation techniques to monitor application behavior.
- Execution method: It provides templates for Frida hooks (
Java.use) that modify the execution flow of the target Android application to intercept cryptographic parameters at runtime.
Audit Metadata