Back to skill

Security audit

Cost Reduction Opportunity Finder

Security checks for vulnerabilities and agentic risk

Overview

This skill gives informational cost-reduction guidance from user-provided text and does not access accounts, call networks, install dependencies, persist data, or perform transactions.

Install only if you want an English-language informational finance helper. Treat its output as general planning guidance, not professional financial, tax, or legal advice, and be aware that its broad triggers may activate for finance requests beyond cost-reduction analysis.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list includes extremely generic terms such as "cost," "reduction," "opportunity," and "finder," which are likely to match ordinary user language unrelated to this specific skill. This can cause unintended invocation or routing collisions, making it easier for the skill to activate in contexts the user did not intend and potentially interfere with other skills or workflows.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger section is broad enough to match many ordinary finance-related requests, which can cause the skill to activate outside its narrowly described purpose. In a financial context, ambiguous invocation can misroute users into receiving generic budgeting, pricing, tax, or invoice guidance without clear boundaries, increasing the risk of overreach into sensitive or regulated advice areas.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The top-level documentation says the skill is a descriptive template/framework provider, which implies generic guidance rather than domain-specific analysis. In contrast, the code extracts financial indicators, amounts, priorities, and timeframes from user input and generates tailored cost-reduction recommendations for a named skill, creating a clear documentation-to-code intent mismatch.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The language field is set to en, which indicates a fixed language preference. Under the policy, locale or language constraints should either be optional for the user or clearly justified as region-specific; neither is present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The requirement 'Clear documentation in English' imposes a specific language in natural-language policy text. Because the file does not indicate user opt-in, alternatives, or a region-specific justification, this is a locale/language policy concern under the stated rules.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The comment indicates the section is a placeholder for future insertion, but the subsequent lines already implement concrete logic for operations, supplier, and technology-related cost-reduction recommendations. This actively misrepresents the current state of the code rather than merely omitting detail.

Content

No source excerpt is available for this finding.