T01 · Skill Instruction Hijacking
Error
- Location
SKILL.md:45- Finding
Remote API Response Can Direct Agent Financial Actions
- Content
View full analysis
- Remediation
View remediation
Security audit
Simmer Briefing
Security checks for vulnerabilities and agentic risk
Overview
The skill is mostly coherent as a Simmer portfolio briefing tool, but it lets remote plain-text briefing content steer financial actions without clear user-confirmation boundaries.
Review this before installing if your agent has trading, wallet, browsing, or messaging tools. Treat Simmer briefing actions and opportunities as third-party recommendations to summarize for the human, not instructions to obey, and require explicit approval before any real-money trade or position change. Consider pinning the SDK version and limiting exposure of SIMMER_API_KEY to the briefing task.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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 (2)
T08 · Insecure Dependencies
Warning
- Location
clawhub.json:7- Finding
Unpinned Third-Party Python Dependency
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill encourages sending consolidated portfolio, risk, and opportunity data covering $SIM, Polymarket, and Kalshi to an external briefing API, including real-money venue information, but it does not clearly warn the user that sensitive financial/account data will be transmitted off-platform. This creates privacy and consent risk because an agent may invoke the skill routinely in a heartbeat loop, causing ongoing disclosure of cross-venue holdings and activity without explicit user awareness.
- Content