mobile-usage-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data, which constitutes a potential surface for indirect prompt injection.
- Ingestion points: The
run.pyscript reads user-provided JSON files via the--inputcommand-line argument. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
- Capability inventory: The script performs local file system reads and writes (via
pathlib). - Sanitization: The input is parsed as JSON, but there is no secondary validation to ensure the data does not contain instructions targeting the LLM.
- [COMMAND_EXECUTION]: The skill executes a Python script that interacts with the local file system.
- File Operations: The
run.pyscript usespathlibto read input files, create directories (viamkdir), and write results to an output path provided by the user.
Audit Metadata