android-intent-security
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to audit external source code and
AndroidManifest.xmlfiles, which serves as an ingestion surface for untrusted data that could contain malicious instructions. - Ingestion points: Auditing of
AndroidManifest.xmlcomponents (Activities, Services, Receivers) and source code handling incoming Intents inonCreateoronNewIntent. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the audited data.
- Capability inventory: The skill provides logic and patterns for code analysis but does not possess or request dangerous capabilities such as network access, arbitrary file writing, or shell execution.
- Sanitization: The skill explicitly mandates the use of
IntentSanitizerand signature verification to process incoming data safely.
Audit Metadata