apktool
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Android packages, creating a surface for potential instruction injection. However, this risk is inherent to the skill's primary purpose of security auditing.\n
- Ingestion points: Android manifest files, resource-derived endpoints, and smali code (SKILL.md).\n
- Boundary markers: None specified in the instructions.\n
- Capability inventory: Reading and writing to the target's artifact directory.\n
- Sanitization: No explicit sanitization of the inspected content is mentioned.\n- [SAFE]: The skill's instructions focus on legitimate local static analysis tasks for security research. No evidence of unauthorized command execution, data exfiltration, or obfuscated code was found.
Audit Metadata