r8-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands, specifically
./gradlewtasks (e.g.,:app:analyzeReleaseR8ConfigandassembleRelease) and local Python scripts to generate and analyze performance data. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from Android project files while maintaining the capability to execute shell commands, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill is instructed to inspect
build.gradle,build.gradle.kts,gradle.properties,libs.versions.toml, andproguard-rules.pro(specified in Step 1 and Step 2 ofSKILL.md). - Boundary markers: None identified; the instructions do not specify the use of delimiters or 'ignore' instructions for the content of these files.
- Capability inventory: The skill possesses significant capabilities, including executing subprocesses via Gradle and Python, writing to the filesystem at
tmp/r8analysis/, and performing complex logic through multiple scripts. - Sanitization: There is no evidence of sanitization or validation of the data read from these project files before it is processed by the analysis logic.
Audit Metadata