kuikly-recomposition-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions and
references/log-retrieval.mdcontain shell commands for retrieving log files from external devices usingadb(Android),xcrun(iOS), andhdc(HarmonyOS). These commands are intended to be executed in the user's local environment to facilitate performance analysis. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could be controlled by an attacker, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads
profiler_report.json,profiler_frames.jsonl, and local Kotlin (.kt) source files located via glob patterns. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the processed files are provided in the skill logic.
- Capability inventory: The skill utilizes file read/write operations, glob file searching, and local shell command execution.
- Sanitization: There is no evidence of sanitization or validation of the content within the ingested performance logs or source code before processing.
Audit Metadata