Back to skill

Security audit

Pact Skill

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill describes an agent trust-negotiation protocol and does not contain hidden execution, persistence, or safety-bypass instructions.

Before using this skill in a real workflow, review any separate implementation of the referenced SDK and be aware that signatures, payments, and on-chain attestations can have lasting external effects. The submitted skill text itself is not executable and does not request hidden authority.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
90% confidence
Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md
- Creating capability-locked session tokens with automatic expiry

## Notes
- SOUL constraints override PACT sessions — never use PACT to bypass safety rules
- Every PACT session produces an EAS attestation on Base (on-chain audit trail)
- Integrates with LAX for discovery and DRS for deal receipts

Instruction Override

High
Category
Prompt Injection
Confidence
90% confidence
Finding

This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md
- Creating capability-locked session tokens with automatic expiry

## Notes
- SOUL constraints override PACT sessions — never use PACT to bypass safety rules
- Every PACT session produces an EAS attestation on Base (on-chain audit trail)
- Integrates with LAX for discovery and DRS for deal receipts

Self-Modification

High
Category
Rogue Agent
Confidence
90% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md
- Creating capability-locked session tokens with automatic expiry

## Notes
- SOUL constraints override PACT sessions — never use PACT to bypass safety rules
- Every PACT session produces an EAS attestation on Base (on-chain audit trail)
- Integrates with LAX for discovery and DRS for deal receipts