mlb-beginner-translator

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill references absolute local file paths specific to the author's environment.
  • Evidence: SKILL.md and resources/methodology.md reference files at /Users/kushaldsouza/Documents/Projects/yahoo-mlb/CLAUDE.md and /Users/kushaldsouza/Documents/Projects/yahoo-mlb/context/frameworks/beginner-glossary.md.
  • Risk: Hardcoded absolute paths are a security and portability risk, potentially leading to unauthorized local file access or leakage of the user's local directory structure if executed on a different machine.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to process and rewrite untrusted content from other agents.
  • Ingestion points: SKILL.md (Step 1) confirms the skill receives a "raw draft from upstream agent" as its primary input.
  • Boundary markers: Absent. The instructions do not define delimiters or tags to isolate the untrusted input from the agent's core instructions.
  • Capability inventory: The skill has the capability to scan, gloss, and rewrite text, which could be manipulated by malicious instructions in the input draft.
  • Sanitization: Absent. There is no evidence of validation or sanitization of the input content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 01:25 PM