release-android
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to process external, potentially untrusted data sources such as application manifests and dependency metadata which could contain embedded instructions.
- Ingestion points: Android manifest files, dependency metadata, and build resources (SKILL.md).
- Boundary markers: None provided in the instructions to separate untrusted data from the agent's operational instructions.
- Capability inventory: The agent is instructed to perform build execution, signature verification, and artifact inspection tasks (SKILL.md).
- Sanitization: No specific sanitization or validation steps are defined for handling the external content during the inspection process.
Audit Metadata