ClawHub
Back to skill

Security audit

Instagram Agent - powered by Teneo Protocol

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent for using a paid Teneo Instagram data agent, but it asks users to install a mutable SDK and connect wallet-backed automatic USDC payments with limited local scoping details.

Review this before installing if you plan to connect a real wallet. Use pinned package versions and a lockfile, avoid exposing unrelated environment variables, prefer an external or hardware signer, and independently confirm every network, token, recipient, amount, and spending limit before approving payments. Do not submit sensitive monitoring targets or regulated personal data unless you are authorized and comfortable with Teneo-operated infrastructure processing those requests.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:99
Finding

Unpinned Third-Party SDK Used in a Wallet-Enabled Payment Flow

Content
View full analysis
Remediation
View remediation
dotenv@ ``` 2. Commit a package lockfile and require reproducible installation with `npm ci`. 3. Validate lockfile integrity in CI and use a trusted registry with namespace and package-access controls. 4. Audit the pinned SDK and its transitive dependency tree before deployment. Repeat the review for every dependency update. 5. Enable automated dependency monitoring, but require security review and testing before merging updates. 6. Include wallet integration guidance in a version-controlled, reviewable document instead of relying exclusively on mutable external instructions. 7. Prefer an external or hardware signer that does not expose private keys to the Node.js process. 8. Apply least privilege to the runtime account and avoid making unrelated credentials or sensitive environment variables available to the SDK process. 9. Before every signature, independently display and validate the chain ID, token contract, recipient, amount, nonce, and calldata. Reject unexpected networks or contracts. 10. Implement explicit spending limits, destination allowlists, and user confirmation for payment transactions. 11. Document precisely what wallet information is accessed, transmitted, or retained, and support security claims with auditable implementation evidence. ]]>

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill encourages sending Instagram usernames, URLs, hashtags, and receiving scraped profile/comment data through an external Teneo Protocol service, but it does not clearly warn users that their queries and returned data are transmitted to a third-party backend over WebSocket. This can mislead users about privacy expectations, especially when the data may include sensitive research targets, monitoring subjects, or regulated personal data despite being 'public' content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.