android-legacy-state
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze Android source code files, which creates a potential surface for instructions embedded within the analyzed data to influence agent behavior.
- Ingestion points: The skill metadata in
SKILL.mdtriggers analysis for**/*Fragment.ktand**/*Activity.ktfiles. - Boundary markers: The instructions lack explicit delimiters or guidance to the agent to ignore instructions found within the comments or strings of the ingested code files.
- Capability inventory: The skill enables the agent to perform code review and generation tasks for Android components as specified in
SKILL.mdandreferences/implementation.md. - Sanitization: There are no sanitization or validation protocols defined for the content of the analyzed source code files.
Audit Metadata