Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward bet-slip parser that produces structured JSON and does not install code, persist data, or perform hidden actions.
Install this if you want an agent to parse bet slips into JSON. Be aware it may process sensitive gambling details such as stake, odds, sportsbook, and the raw bet text; review the JSON before letting another skill store or act on it.
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
print(f'Expected payout: {payout:.2f}')"
## Output Rules
1. Always output a valid JSON object matching the schema
2. All odds must include American format (convert if needed)
The phrase "log this bet" is ambiguous because logging may imply persistence, downstream automation, or record creation, but the skill does not clearly constrain when it should activate versus when another storage-oriented skill should handle the request. This ambiguity can cause overbroad routing and accidental processing of user data outside the user's precise intent.
The trigger phrase "I just bet..." or similar everyday betting statements is broad enough to activate on casual conversation rather than an explicit request to parse a bet slip. In an agent environment, this can cause unintended skill invocation, leading to inappropriate data extraction, logging, or downstream actions on sensitive gambling-related content.