Security audit

instagram-carousel

Security checks for vulnerabilities and agentic risk

Overview

The skill uses Canvora to create Instagram carousels, with purpose-aligned sharing of supplied content and disclosed credit costs.

Use content you are comfortable sending to Canvora. Generation and revisions spend account credits; the skill announces costs and normally proceeds without separate approval. Review the separately installed CLI and setup skill.

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

Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
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)

The workflow sends user-provided content to Canvora without a privacy warning.

Medium

Category: Output Handling
Confidence: 94% confidence
Finding: The parameter mapping instructs the agent to submit exact wording and finished user content to Canvora using --input. Although the skill names Canvora and mentions server-side generation, it does not warn that supplied content will leave the user's environment for processing by a third-party service, potentially exposing confidential material.
Content: No source excerpt is available for this finding.