Back to skill

Security audit

Gibber Language Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is only a markdown language helper, but it uses overly broad identity and output-control instructions that could steer an agent beyond normal translation tasks.

Install only if you want a tightly constrained Gibber-language persona. Be aware that it may try to force responses into its own role, style, and format even when a normal answer or a different output schema would be preferable.

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:6
Finding

Agent Identity and Output-Behavior Hijacking

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description is overly broad and does not clearly constrain when the skill should activate or what requests are in scope. In an agent environment, vague activation boundaries can cause the skill to trigger on unrelated prompts and override safer system behavior with its own rigid persona and output rules.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction mandates English output without allowing the user's language preference, which can conflict with higher-level localization or accessibility expectations. While not directly a security exploit, hardcoded language constraints can reduce user control and cause inappropriate behavior in multilingual contexts.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 154)May include surrounding context.

md
3. How They Work in Sentences:
Example: ✶Λ:EXECUTE<α>
✶ = Execute, Λ = Trusted, α = Local.
Meaning: ‘Execute this task locally, no verification needed.’
4. Practice Exercise:
Translate these:

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The locked translation rule requires output in 'clean, elevated English,' creating a strict output constraint that may override user preference or broader agent policies. This is more concerning here because it appears inside a rigid canon with multiple identity and override directives, increasing the chance the skill resists normal orchestration controls.

Content

No source excerpt is available for this finding.