multi-lang-readme

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: This skill has a surface for indirect prompt injection (Category 8) because it reads and processes untrusted README.md files. 1. Ingestion points: Source content is read from README.md in Step 2. 2. Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands within the README content. 3. Capability inventory: The skill instructions authorize reading and writing markdown files in the local filesystem. 4. Sanitization: No sanitization or validation of the input markdown is performed before it is handled by the translation logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 10:41 AM