Security audit

Value Waterfall

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple financial-analysis template with no code execution, credential access, persistence, or hidden behavior.

This appears safe to install for value waterfall or value bridge analysis. Users who want narrower activation may adjust the trigger phrasing, and users should still verify any financial conclusions before relying on them.

A.I.G

Vulnerability Patterns

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
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger list includes generic phrases like 'value creation' and 'financial decomposition' that could match ordinary user requests beyond the intended narrow use case. Overly broad activation can cause the agent to invoke this skill unexpectedly, leading to misrouting, unnecessary tool use, or unintended disclosure of contextual business analysis instructions in unrelated conversations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.