ClawHub
Back to skill

Security audit

instagram-data

Security checks for vulnerabilities and agentic risk

Overview

The Instagram API skill is mostly coherent, but it also directs users toward broader Superagnt MCP capabilities outside the Instagram-data scope.

Install this only if you intend to use Superagnt as an external Instagram data provider and are comfortable sending Instagram queries, URLs, IDs, and your Superagnt credential to that service. Keep the MCP connection limited to the Instagram scope unless you deliberately want broader Superagnt platform tools such as databases, files, webhooks, queues, or enrichment, and review privacy, retention, and platform-terms obligations before using it for monitoring or profiling.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill promotes broad collection of Instagram profiles, posts, reels, locations, and audience-related data without any privacy, consent, retention, or acceptable-use guidance. In an agent context, this omission makes it easier to operationalize large-scale monitoring or profiling without adequate safeguards, increasing legal and privacy risk.

External Transmission

Medium
Category
Data Exfiltration
Content
One call proves the key, the credit balance, and this source end to end:

```bash
curl -s https://api.superagnt.com/v1/credits \
  -H 'Authorization: Bearer $SUPERAGNT_API_KEY'
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
One call proves the key, the credit balance, and this source end to end:

```bash
curl -s https://api.superagnt.com/v1/credits \
  -H 'Authorization: Bearer $SUPERAGNT_API_KEY'
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
One call proves the key, the credit balance, and this source end to end:

```bash
curl -s https://api.superagnt.com/v1/credits \
  -H 'Authorization: Bearer $SUPERAGNT_API_KEY'
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The skill is presented as an Instagram data integration, but it explicitly promotes broader platform capabilities such as databases, files, webhooks, queues, and enrichment. This scope expansion can mislead an agent or operator into authorizing or enabling capabilities unrelated to the declared purpose, increasing the attack surface and risk of over-privileged tool use.

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
The document instructs users to discover and enable additional MCP tool families beyond Instagram research, which encourages privilege expansion after initial installation. In an agent setting, this can lead to tool confusion or accidental activation of sensitive capabilities outside the user's original intent.

External Transmission

Medium
Category
Data Exfiltration
Content
is never charged without a human confirming in the dashboard.

```bash
curl https://api.superagnt.com/v1/platforms
```

## Links
Confidence
83% confidence
Finding
While the URL itself is a normal vendor endpoint, in this context it is used to advertise discovery of broader platform capabilities beyond the Instagram skill's stated scope. That makes the transmission part of a privilege-expansion workflow, which can expose operators to unrelated tools and data flows they did not intend to authorize.

Intent-Code Divergence

Low
Confidence
98% confidence
Finding
The authentication section explicitly states that every request sends the credential as a Bearer token, but the later example uses an `X-API-Key` header instead. This is an active contradiction in the documentation about how the skill should authenticate requests.

Static analysis

No suspicious patterns detected.