sync-testing-skill

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from the codebase.
  • Ingestion points: The skill reads source code files from packages/[PACKAGE]/**/*.spec.{ts,tsx}.
  • Boundary markers: There are no defined delimiters or instructions to ignore embedded commands within the test files, which could lead the agent to follow malicious instructions hidden in code comments.
  • Capability inventory: The skill has file read and write access for documentation purposes. It does not have network access, nor does it use shell execution tools or dynamic code evaluation.
  • Sanitization: No sanitization or escaping of the content read from the codebase is performed before it is processed and added to the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 01:21 AM