T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:28- Finding
Bearer Credential Disclosure Through an Unrestricted API Base URL
- Content
View full analysis
- Remediation
View remediation
Security audit
Alphagbm Macro View
Security checks for vulnerabilities and agentic risk
Overview
This skill is coherent for AlphaGBM macro tracking, but it deserves review because it uses sensitive portfolio-linked analysis, an API key, broad triggers, and an overrideable API destination.
Install only if you are comfortable connecting this agent to AlphaGBM with an API key and having macro analysis tied to your portfolio or profile data. Use a tightly scoped key, keep ALPHAGBM_BASE_URL pointed only at the official service, and confirm add/remove actions or portfolio-linked lookups when the prompt is ambiguous.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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)
T01 · Skill Instruction Hijacking
Warning
- Location
SKILL.md:143- Finding
Untrusted Remote Impact Analysis Is Presented Without Prompt-Injection Controls
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)
Tool Parameter Abuse
High
- Category
- Tool Misuse
- Confidence
- 80% confidence
- Finding
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
- Content
3. Remove indicator
text DELETE /api/research/macro/<INDICATOR_KEY>Uses the key (
VIX, not an id). 404 if not tracked.
Tool Parameter Abuse
High
- Category
- Tool Misuse
- Confidence
- 80% confidence
- Finding
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
- Content
md → Present each indicator: value, change, impact on their holdings 3. User: "Stop tracking DXY" → DELETE /api/research/macro/DXY 4. User: "Is high VIX hurting my positions?" → GET /api/research/macro → read VIX's impact_analysis field
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The skill advertises AI-generated impact analysis tied to the user's holdings but does not clearly warn users that portfolio-related data may be transmitted to an external AlphaGBM service. This creates a transparency and privacy problem: users may unknowingly authorize disclosure of sensitive holdings information to a third party.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The trigger guidance is broad enough to activate on generic finance terms like "macro", "yield", "VIX", and Chinese equivalents, which can cause the skill to run when the user did not clearly intend to use this external macro-tracking service. In this skill, unintended invocation is more concerning because the workflow includes portfolio-linked impact analysis and external API use, increasing the chance of surprise data processing or unintended state changes.
- Content