Back to skill

Security audit

Signal Skills: outreach

Security checks for vulnerabilities and agentic risk

Overview

ClawScan judged this skill benign because the two low-probability findings were marked expected for its purpose, though the overall confidence is medium and some reference checks were incomplete.

The verdict is benign, but it is not a guarantee of safety. Skillspector scanned all five listed components, yet the analysis was partial because two local path references could not be resolved. Consider whether file access fits your needs, and remember that the results do not establish what permissions the host runtime enforces.

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 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 (2)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 · references/outreach-framework.md (reported line 9)May include surrounding context.

md
1. **Evidence-grounded:** Every message references a specific public signal. No coldGeneric outreach.
2. **Respectful of time:** Short messages, one question per touch, easy to ignore.
3. **Never automated without consent:** This skill writes drafts. The human sends them.
4. **No private information:** Only reference what the prospect posted publicly and intentionally.
5. **Tone-matching:** Mirror the prospect's communication style from their public content.