kalshi

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the external Kalshi public API (api.elections.kalshi.com), which contains user-influenced or third-party content like market descriptions.
  • Ingestion points: Responses from market searches, event listings, and candlestick history queries defined in SKILL.md and references/api-reference.md.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent processes API output.
  • Capability inventory: The skill performs shell execution via the sports-skills CLI and Python execution through the sports_skills.kalshi module.
  • Sanitization: The scripts/validate_params.sh script validates ticker formats and ensures required parameters like timestamps are present for specific commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 02:55 PM