Back to skill

Security audit

revops

Security checks for vulnerabilities and agentic risk

Overview

This RevOps skill is a documentation-only guide for lead lifecycle, CRM workflow, routing, scoring, and dashboard design, with expected but privacy-sensitive business automation advice.

Installers should treat this as a RevOps playbook, not an automation executor. Before implementing its workflows, confirm which CRM, Slack/email channels, webhook destinations, enrichment tools, and ad audiences are approved for lead and customer data, and add review steps before bulk reassignment, archiving, retargeting, or external data sharing.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description says to use the skill for 'anything involving the systems and processes that connect marketing to revenue,' in addition to broad phrases like 'help with revenue operations.' This lacks clear scope boundaries or exclusion conditions, increasing the chance of unintended invocation for adjacent sales, marketing, or operations topics.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 227)May include surrounding context.

md
| Deal Size | Approval Required |
|-----------|-------------------|
| Standard pricing | Auto-approved |
| 10-20% discount | Sales manager |
| 20-40% discount | VP Sales |
| 40%+ discount or custom terms | Deal desk review |

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This JSON eval file is a manifest-type file, so vague-trigger review applies. The expected behavior explicitly says the skill should 'trigger on casual phrasing,' and the paired example prompt is broad everyday language rather than a specific invocation, which increases the risk of unintended activation.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
80% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · references/automation-playbooks.md (reported line 30)May include surrounding context.

md
1. Send internal email to contact owner: "SLA warning: [Contact Name] has not been contacted"
2. If still no activity after 24 hours → send alert to sales manager
3. If still no activity after 48 hours → reassign contact owner via rotation
4. Create task for new owner: "Urgent: Contact [Contact Name] — reassigned due to SLA breach"
**Outcome:** No MQL goes unworked for more than 48 hours
**Notes:** Exclude contacts where last activity type is "Call" or "Meeting" (already engaged)

Session Persistence

Medium
Category
Rogue Agent
Confidence
80% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · references/automation-playbooks.md (reported line 73)May include surrounding context.

md
1. Send internal email to contact owner: "SLA warning: [Contact Name] has not been contacted"
2. If still no activity after 24 hours → send alert to sales manager
3. If still no activity after 48 hours → reassign contact owner via rotation
4. Create task for new owner: "Urgent: Contact [Contact Name] — reassigned due to SLA breach"
**Outcome:** No MQL goes unworked for more than 48 hours
**Notes:** Exclude contacts where last activity type is "Call" or "Meeting" (already engaged)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The playbooks repeatedly instruct sending lead and customer context through internal email, Slack, and third-party webhooks without any guidance on data minimization, access controls, retention, or approved-use boundaries. In a RevOps automation context, this can expose PII, behavioral activity, deal details, and customer data across systems and recipients beyond least-privilege, creating privacy, compliance, and inadvertent data leakage risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.