Back to skill

Security audit

IG Comment Strategist

Security checks for vulnerabilities and agentic risk

Overview

This is a small documentation-only Instagram comment strategy skill with an optional email-report feature; no hidden code, persistence, or destructive behavior was found.

Before using the email feature, treat SMTP credentials as sensitive: store them in environment variables or a secret manager, use TLS-enabled SMTP and app-specific credentials where possible, and confirm report recipients because Instagram URLs, generated comments, and campaign context may be included in emailed reports.

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
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The README advertises sending analysis reports by email but gives no warning about what data may be included, whether Instagram URLs, generated comments, or account-related content could contain sensitive or client information, or how that data is handled in transit and at rest. In a growth-marketing skill that may process multiple campaign URLs and produce reports for agencies or managers, this omission increases the risk of accidental disclosure through misaddressed emails, insecure SMTP configuration, or retention of sensitive report contents.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

Listing SMTP credentials as a requirement without any guidance on secure secret handling can lead users to place usernames/passwords directly in scripts, CLI history, config files, or shared environments. Because this skill is aimed at agencies, managers, and batch workflows, exposed mail credentials could allow unauthorized access to outbound email systems, disclosure of reports, or abuse of the SMTP account for phishing/spam.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly supports email reports and requires SMTP credentials, but the documentation provides no warning about what data may be transmitted, how credentials should be stored, or whether analyzed Instagram URLs/content may be included in outbound emails. This creates a real privacy and secret-handling risk because operators may supply sensitive credentials and send potentially sensitive analysis data through email without understanding retention, exposure, or transport implications.

Content

No source excerpt is available for this finding.