T09 · Insecure Skill Coding Practices
Error
- Location
scripts/scan-edges.js:74- Finding
Index-Based Odds Mapping Can Invert Financial Recommendations
- Content
View full analysis
- Remediation
View remediation
Security audit
Prediction Market Trader
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed Kalshi trading toolkit, but it exposes live financial actions and fragile market-matching logic without the safeguards its own docs describe.
Review this carefully before installing. Use read-only or test credentials where possible, avoid putting private keys directly into shell history, and do not let an agent place or cancel real Kalshi orders through this skill unless you have added explicit confirmation, dry-run defaults, order-size limits, exposure checks, and reliable market-participant matching.
Vulnerability Patterns
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (3)
T09 · Insecure Skill Coding Practices
Error
- Location
scripts/scan-edges.js:82- Finding
Ambiguous Surname Matching Can Associate Odds with the Wrong Kalshi Market
- Content
View full analysis
- Remediation
View remediation
T09 · Insecure Skill Coding Practices
Error
- Location
scripts/kalshi-auth.js:91- Finding
Live Order Function Does Not Enforce Documented Trading Safety Controls
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/scan-edges.js --category tennis
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md node scripts/scan-edges.js --category tennis
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 94% confidence
- Finding
The skill describes capabilities that rely on environment variables and outbound network access, but it does not declare any explicit tool scope or permissions boundaries. In an agent setting, this increases the chance that a host will grant broader-than-necessary access, enabling unintended credential access or live API interaction without clear user consent.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The skill promotes live order execution and credential handling for a real-money trading platform without an explicit warning that actions may place actual trades and cause financial loss. In this context, omission of a risk warning is dangerous because users or agents may treat examples as safe defaults and trigger irreversible market actions.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The quick-start instructions tell users to export an RSA private key directly in the shell and then run trading commands, but they do not warn about shell history, process inspection, logging, or safer secret-storage methods. This can expose long-lived credentials that enable unauthorized API access and potentially fraudulent trading on the user's account.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The module exposes
placeOrderandcancelOrderas directly callable functions that execute real trading actions immediately, with no confirmation gate, dry-run mode, policy check, or explicit safeguard against accidental invocation. In the context of an agent skill for automated prediction-market trading, this increases the risk that a prompt, logic error, or unintended tool call can place or cancel live orders and cause financial loss.- Content
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 60% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
js // Get today's scheduled events from Sofascore const today = new Date().toISOString().split('T')[0]; const scheduled = await fetch(`https://api.sofascore.com/api/v1/sport/tennis/scheduled-events/${today}`); if (!scheduled?.events) { console.log('No events found'); return; } // Get Kalshi tennis series
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 60% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
js // Get today's scheduled events from Sofascore const today = new Date().toISOString().split('T')[0]; const scheduled = await fetch(`https://api.sofascore.com/api/v1/sport/tennis/scheduled-events/${today}`); if (!scheduled?.events) { console.log('No events found'); return; } // Get Kalshi tennis series
Static analysis
No suspicious patterns detected.