Back to skill

Security audit

lens

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because the scanner found a schedule-removal policy concern and could not fully inspect three scripts; confidence is medium.

Consider avoiding installation until the scripts can be fully reviewed and schedule removals are clearly limited and reported to you. The verdict is suspicious, not malicious, and the partial scan means it cannot establish that the skill is safe.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (5)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md
on`) is missing from `OPENCLAW_CRON_LIST`, run `node` on [scripts/bootstrap.js](./scripts/bootstrap.js) from this skill directory (outside the workspace sandbox

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

md
view.runner` is not `"none"`), immediately run `node` on [scripts/interview.js](./scripts/interview.js) and execute [prompts/interview.md](./prompts/interview.m

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

md
n Distillation (*"Distill my LENS"*):** Run `node` on [scripts/distillation.js](./scripts/distillation.js) from this skill directory (outside the workspace sand

Scheduled jobs can be removed without notifying the user.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The protocol explicitly authorizes deleting jobs identified in script output but requires user notification only for registrations and updates, leaving deletion-only changes silent. Although schedule reconciliation is legitimate for this skill, this omission can conceal the disabling of recurring tasks; the prompt also provides no explicit restriction that removal targets must be LENS-owned jobs.

Content

No source excerpt is available for this finding.

Permission 'network' is declared but no corresponding code capability (network) was detected.

Low
Category
MCP Least Privilege
Confidence
65% confidence
Finding

Declared permissions with no matching code capability may indicate removed functionality or pre-staging for future abuse.

Content

No source excerpt is available for this finding.