md-translator

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Potential for indirect prompt injection identified through the processing of external document content.
  • Ingestion points: Reading of local Markdown files as defined in Step 1 of SKILL.md.
  • Boundary markers: No delimiters are used to separate user data from instructions, and no warnings are provided to the agent to ignore embedded commands.
  • Capability inventory: The skill utilizes file system tools for reading and writing data.
  • Sanitization: No input validation, escaping, or filtering of the processed content is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 12:46 PM
Security Audit — agent-trust-hub — md-translator