sast-detekt
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
detektand./gradlewto perform static analysis. These are standard development tools and are used as intended for the skill's primary purpose.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes Kotlin source code and scan results. Maliciously crafted Kotlin code could potentially influence the agent's summary if the findings are not properly delimited.\n - Ingestion points: Kotlin source directory and
detekt-results.jsonoutput file.\n - Boundary markers: Findings are presented in a markdown table format to the agent.\n
- Capability inventory: Shell command execution (
detekt,./gradlew).\n - Sanitization: No explicit sanitization or filtering of rule descriptions or findings is defined to mitigate malicious content in the source files.
Audit Metadata