Security audit

Analyze Competitor Wins & Losses — Win/Loss Analysis Automation

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly purpose-aligned, but it asks users to connect sensitive CRM, support, email, Slack, and reporting systems while its safety guidance is incomplete.

Install only if the operators are authorized to process the connected CRM, support, email, survey, and Slack data. Use least-privilege read scopes where possible, redact customer identifiers and deal-sensitive fields before analysis or posting, confirm every Slack/email recipient for scheduled reports, and review external collection practices against legal and internal competitive-intelligence rules.

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

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 (4)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.
md
"files": ["SKILL.md"],

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill explicitly encourages ingestion of CRM records, churn interviews, support conversations, survey responses, emails, and Slack threads, all of which can contain sensitive customer, employee, and commercial data. Without a clear user-facing privacy notice, minimization guidance, or consent/handling boundaries, operators may unintentionally expose regulated or confidential information to the model and downstream integrations.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill describes scheduled reports and Slack notifications that may automatically broadcast competitive analysis, deal details, churn reasons, and customer quotes to channels or recipients. Without an explicit warning or approval step, sensitive internal sales intelligence or customer information could be sent to broader audiences than intended.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The skill promotes automatic scraping and monitoring of competitor pricing pages and release information without noting legal, contractual, or compliance constraints. While this is not inherently malicious, omitting terms-of-service and collection-boundary guidance can lead users to perform impermissible external data collection or create avoidable legal/compliance exposure.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.