Back to skill

Security audit

basal-ganglia-memory

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable development placeholder that discloses a future external API dependency but does not currently perform data access, persistence, or transmission.

Safe to treat as a placeholder skill. Before using a future implemented version or setting SKILLBOSS_API_KEY, review what prompts, memory, and agent context are sent to SkillBoss API Hub, how they are retained, and whether use is opt-in and reversible.

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 (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The file names a specific external endpoint and states that the skill will use it for all AI capabilities with API-key-based authentication. In agent ecosystems, this creates a real risk of external transmission of potentially sensitive prompts, memory content, or operational context, especially because the skill is memory-related and may handle durable or user-derived data.

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

md
Based on neuroscience research on the basal ganglia's role in procedural learning and habit formation.

When implemented, this skill will use **SkillBoss API Hub** (`https://api.skillbossai.com/v1/pilot`) for all AI capabilities, authenticated via `SKILLBOSS_API_KEY`.

---

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill documentation explicitly states that, once implemented, all AI capabilities will be routed through an external API and authenticated with an environment secret, but it provides no user-facing warning about data sharing, retention, or privacy implications. Even though this is only a planned behavior in documentation, it signals a design that may send prompts or sensitive context off-host without informed consent, which is a legitimate privacy and security concern.

Content

No source excerpt is available for this finding.