Back to skill

Security audit

Cognitive Comm Advisor

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill provides disclosed workplace communication advice using personality heuristics and does not request code execution, credentials, network access, persistence, or privileged actions.

Install only if you are comfortable using personality-type heuristics for workplace communication. Treat its advice as a planning aid, not a psychological assessment or a reliable basis for judging coworkers.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The instructions require a mandatory self-check before sending any non-English output and enforce translation behavior for Chinese and other languages without indicating user choice or opt-in. This is a natural-language policy concern because it imposes locale-specific output rules rather than offering language selection.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file explicitly instructs the skill to produce flattering, type-based personality portraits as if they meaningfully describe the user, without caveats about uncertainty, stereotyping, or the weak reliability of MBTI-style typologies. In a workplace communication advisor, this can nudge users to over-trust psychological profiling, reinforce bias about themselves or others, and shape real interpersonal decisions on a potentially inaccurate basis.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.