Back to skill

Security audit

elgora-solver-skill

Security checks for vulnerabilities and agentic risk

Overview

ClawScan’s verdict is benign: the scans reported no AIG findings, while Skillspector noted behavior that may not match the skill’s stated purpose; some evidence is incomplete.

The verdict is benign, with medium confidence. Before installing, consider whether the reported bounty discovery and notification subscription features fit your needs. Skillspector’s review was partial because some references could not be resolved, so the available evidence does not fully cover those references.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied commands manage notification subscriptions rather than preparing or submitting files, reading finalized outcomes, or claiming awards. Registering a webhook and managing filtered subscriptions is a distinct, undeclared capability, not merely an implementation detail of the stated submission workflow.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The supplied commands concern finding solvable bounties. They contain no file preparation, private submission, finalized-outcome retrieval, or award claiming. Although bounty discovery could support a broader solver workflow, it is the entire behavior shown here and is materially different from the declared purpose. No unrelated resource access or additional permissions are evident.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 434)May include surrounding context.

md
reports as unsupported.

Use the
[latest public Solver bundle](https://elgora.ai/skills/elgora-solver-skill/SKILL.md)
when a newer release is available.