jvmname-disambiguate-erased-overloads
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides shell scripts that use common Unix utilities (grep, sed, sort, uniq) to perform static analysis on local Kotlin source code.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted local source files, creating a potential surface for indirect prompt injection. 1. Ingestion points: Local .kt files are read using grep (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: The skill utilizes shell command execution (grep, sed, sort, uniq, printf) (SKILL.md). 4. Sanitization: Implicit sanitization is provided by the regex patterns used to match specific Kotlin syntax.
Audit Metadata