typescript-expert
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands for environment discovery and validation, including node evaluations and linter runs in SKILL.md. The script scripts/ts_diagnostic.py uses subprocess.run with shell=True to execute system utilities for version checking and file searching.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by ingesting and analyzing untrusted project data. 1. Ingestion points: Reads package.json, tsconfig.json, and TypeScript source files within scripts/ts_diagnostic.py and SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Shell execution via subprocess.run in Python and node -e evaluators in markdown. 4. Sanitization: Absent.
Audit Metadata