mlb-data
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill setup involves installing the 'sports-skills' Python package. This package is recognized as a vendor-owned resource matching the author 'machina-sports'.
- [COMMAND_EXECUTION]: The skill facilitates the execution of the 'sports-skills' CLI tool for data retrieval. It also includes a shell script 'scripts/validate_params.sh' that uses standard commands like 'grep' and 'cut' to validate dates and parameters.
- [PROMPT_INJECTION]: The skill ingests data from external ESPN endpoints, which creates an attack surface for indirect prompt injection. 1. Ingestion points: Scores, news headlines, descriptions, and game summaries from ESPN APIs (referenced in SKILL.md). 2. Boundary markers: No specific delimiters or 'ignore embedded instructions' warnings are present in the documentation for handling the external data. 3. Capability inventory: Execution of the 'sports-skills' CLI tool. 4. Sanitization: No explicit sanitization or validation of the content fetched from external APIs is mentioned.
Audit Metadata