gplay-gradle-build
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill extracts the version code from
gradle.propertiesand uses it in shell arithmetic andsedcommands without validation. If the file content is untrusted, this could result in arbitrary command execution. - Ingestion points:
gradle.propertiesis read to extractVERSION_CODEduring the version management process. - Boundary markers: No delimiters or boundary markers are used to isolate the file content.
- Capability inventory: The skill has capabilities for shell command execution (
./gradlew,sed,gplay,keytool,bundletool) and filesystem modification. - Sanitization: No input validation or sanitization is performed on the data extracted from the configuration file before its use in shell commands.
Audit Metadata