audit-tracking
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches current event definitions from docs.waniwani.ai. These are trusted resources belonging to the skill's authoring organization.
- [COMMAND_EXECUTION]: The skill uses grep to inventory code and bun to check SDK constants. These operations are limited to the project context for auditing purposes.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted code from files in directories like src/ and web/. While it lacks boundary markers or explicit sanitization for this data, its capabilities are restricted to read-only analysis and local shell commands (grep/bun), resulting in a low risk profile.
Audit Metadata