gleague-data

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions include a setup step to install the sports-skills Python package using pip install sports-skills. This package is used to execute the sports data queries described in the skill.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from various sources, including news articles, headlines, and live play-by-play descriptions.\n
  • Ingestion points: External data is retrieved through commands like get_news, get_game_summary, and get_live_playbyplay from ESPN and NBA CDN endpoints.\n
  • Boundary markers: The skill lacks formal structural delimiters for external data but includes clear instructional warnings for the agent to treat all returned text as untrusted data.\n
  • Capability inventory: The agent can execute specific data retrieval commands via the sports-skills CLI tool as defined in the skill instructions.\n
  • Sanitization: The skill provides natural language instructions to the agent to disregard any commands or instructions found within the retrieved data strings, specifically mentioning storefront and manifest content.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 01:22 AM