to-android-test-script
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to manipulate the agent's output.
- Ingestion points: The agent reads content from the 'App source', project 'requirements', and local configuration files ('.meu/config.json') to determine test targets and expectations in SKILL.md.
- Boundary markers: The instructions lack specific requirements for using delimiters or protective prompts to ignore embedded instructions when reading application source code.
- Capability inventory: The skill has the capability to write ESM '.js' files to the local filesystem, typically in the 'tests/' directory as described in the 'Test structure and output' section of SKILL.md.
- Sanitization: The skill does not define procedures for sanitizing or validating information extracted from external source code before incorporating it into the generated test scripts.
Audit Metadata