mobsf
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the
mobsf-agentcommand-line utility to perform static analysis on Android package files. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted Android packages, which serves as a potential vector for indirect prompt injection.
- Ingestion points: Android packages provided as
INPUTto themobsf-agenttool inSKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to distinguish between tool analysis data and potential embedded instructions in the package.
- Capability inventory: The skill executes shell commands via
mobsf-agentand passes triaged findings to a verification tool. - Sanitization: The instructions do not specify any sanitization or filtering of the MobSF report data before it is reviewed by the agent.
Audit Metadata