re-apk
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill guides the user to fetch tools from reputable GitHub repositories such as
skylot/jadx,iBotPeaches/Apktool, andpxb1988/dex2jar. These are standard tools for Android reverse engineering. - [COMMAND_EXECUTION]: The workflow requires the execution of various shell commands to install tools (using
apt,brew, orpacman), perform analysis (jadx,apktool), and interact with Android devices (adb). - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the analysis of untrusted third-party APK files. This introduces a surface where malicious instructions embedded within an APK's resources or code could be encountered by the AI agent during the analysis process.
- Ingestion points: Tool outputs derived from parsing APK manifests, smali code, and Java source code as described in
SKILL.mdandreferences/commands.md. - Boundary markers: The instructions do not define specific delimiters to separate untrusted tool output from the agent's internal reasoning context.
- Capability inventory: The agent has the capability to execute shell commands, read/write files, and install software packages as outlined in the operational steps.
- Sanitization: No specific sanitization or filtering logic is provided for the output generated by the reverse engineering tools before it is processed by the agent.
Audit Metadata