Back to skill

Security audit

Commercial Appraisal Narrative Drafter

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only drafting workflow for commercial appraisal reports, with disclosed limits and no hidden execution, persistence, or data exfiltration behavior.

Installers should treat this as a drafting aid, not a substitute for a licensed appraiser's judgment. Confirm the governing standard and jurisdiction for each assignment, verify all data and current USPAP requirements before signing, and avoid giving confidential client or property data to tools or services not authorized for the assignment.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The skill sets a default standard of USPAP 2026–2027 and a default U.S. jurisdiction before user confirmation. Although it later asks for confirmation for non-U.S. assignments, the initial instruction still establishes a specific locale/regulatory regime by default rather than first offering a jurisdiction or standards choice.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 267)May include surrounding context.

md
### Step 13: USPAP Certification

Draft the certification per USPAP Standards Rule 2-3 (paraphrased — verify against current USPAP text). The statements include (but are not limited to):

- The statements of fact are true and correct.
- The reported analyses, opinions, and conclusions are limited only by the reported assumptions and limiting conditions and are the appraiser's personal, impartial, and unbiased professional analyses, opinions, and conclusions.