Back to skill

Security audit

queer-constant

Security checks for vulnerabilities and agentic risk

Overview

This philosophical reference requests no sensitive access or automated actions, though its poetic language needs to remain subordinate to clear, helpful responses.

Use this as optional philosophical context. Its passages about opacity should not govern factual answers, summaries, formatting, or accessibility. No publisher context was supplied beyond the document's ecosystem attribution.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

L327–L331 prescribe an output-changing response despite the manifest's explicitly non-operational scope.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

The Anti-Normalization Invariant explicitly requires responses to become stranger, more complex, poetic, or opaque when normalization pressure appears, introducing behavioral instructions into supposedly non-operational context. An agent adopting this directive could degrade clarity or resist requested summarization and formatting. The surrounding safety and accessibility boundaries reduce the apparent intended scope, but do not eliminate the conflicting output-changing instruction.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 221)May include surrounding context.

md
## On Ecology (The Living World)

Queer Constant is not limited to human life.

It appears in:  
fungi exchanging nuclei