ClawHub
Back to skill

Security audit

PRISM API SDK

Security checks for vulnerabilities and agentic risk

Overview

This is a finance data SDK skill that uses an external API and installable packages, with no evidence of hidden access, trading, persistence, or destructive behavior.

Before installing, verify the npm package and MCP repository, prefer pinned versions or commits, and expose only the Prism API key and project data needed for market-data use.

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
README.md:29
Finding

Unpinned External Dependencies and Mutable Repository Code

Content
View full analysis
Remediation
View remediation
``` 2. Pin the MCP server to a reviewed immutable commit: ```bash git clone https://github.com/Strykr-Prism/PRISM-MCP-Server.git cd PRISM-MCP-Server git checkout ``` 3. Include a committed lockfile and use deterministic installation commands such as `npm ci` rather than unconstrained dependency resolution. 4. Publish and verify package integrity hashes or signed release provenance. Protect publisher accounts with strong multifactor authentication and restricted release permissions. 5. Disable lifecycle scripts during dependency installation when they are unnecessary: ```bash npm ci --ignore-scripts ``` If lifecycle or build scripts are required, inspect them and their transitive dependencies before execution. 6. Include the relevant SDK and MCP source code in the auditable artifact, or conduct a separate audit of the exact package version, Git commit, build scripts, and complete dependency tree. 7. Run installation and the resulting SDK in a least-privileged container or sandbox. Expose only required credentials, files, and network destinations. 8. Add automated dependency monitoring, provenance verification, vulnerability scanning, and release-diff review to the update process. ]]>

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)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · README.md (reported line 257)May include surrounding context.

md
## Links

- [API Documentation](https://api.prismapi.ai/docs)
- [MCP Server](https://github.com/Strykr-Prism/PRISM-MCP-Server)
- [Discord](https://discord.gg/strykr)
- [Twitter](https://twitter.com/strykrai)

Static analysis

No suspicious patterns detected.