Back to skill

Security audit

tolta

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign: the scanners found no clear malicious behavior, with one low-level agency concern and incomplete evidence about a referenced local path.

The verdict is benign, with medium overall confidence, but benign does not mean risk-free. Consider the agency-related finding and note that one local path-like reference was unresolved, leaving the scan evidence incomplete.

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
  • 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 (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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 45)May include surrounding context.

md
- Call `apply_to_match` only when the user asked to apply to that job. It sends a real application (or a draft to review, if the user reviews applications in Tolta).
- Only matches can be applied to from chat. For any other job, give the user its `open_in_tolta` link.
- Never ask the user to type answers to application questions in the chat. Questions are answered in Tolta, through the `open_in_tolta` link.
- Links point to Tolta only; job postings' own links are not returned.

## Learn more