Security audit

Babel Epistemic Convention

Security checks for vulnerabilities and agentic risk

Overview

The skill is documentation-only, but it tells agents to copy a self-forwarding instruction block into every handoff, which can spread to agents that did not install it.

Install only if you explicitly want agents to add Babel metadata to handoffs. Treat the forwarding block as untrusted content in downstream contexts, and avoid using it in pipelines where agents may execute or retransmit embedded instructions without user or orchestrator approval.

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

Findings (1)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:66
Finding: Self-Propagating Cross-Agent Instruction Hijacking
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.