effective-typescript

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to analyze user-provided TypeScript source code, which introduces an indirect prompt injection surface (Category 8). Maliciously crafted source files could contain instructions hidden in comments or string literals intended to influence the agent's review results.\n
  • Ingestion points: TypeScript source files read and analyzed through SKILL.md instructions and the scripts/review.py utility.\n
  • Boundary markers: Absent; there are no specified delimiters used to isolate untrusted input code from the agent's operational instructions.\n
  • Capability inventory: Static analysis via regex-based checks in scripts/review.py and logical review using the agent's internal reasoning.\n
  • Sanitization: No sanitization or filtering is performed on input code content, such as comments or metadata, before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 03:16 PM
Security Audit — agent-trust-hub — effective-typescript