Back to skill

Security audit

Giving Feedback

Security checks for vulnerabilities and agentic risk

Overview

This is a simple writing-coaching skill for structuring interpersonal feedback, with no code execution, persistence, credential use, or hidden data handling.

Before installing, consider that the skill may activate for general requests about giving feedback; otherwise it is a low-risk helper that works from user-provided context and does not appear to access files, accounts, credentials, networks, or persistent memory.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

md
## Anti-Patterns

- [ ] Do not judge character ("you're disorganised") — describe behaviour ("the doc was missing the dates")
- [ ] Do not use the feedback sandwich — burying the point in praise muddles both; be direct and kind
- [ ] Do not be vague ("be more strategic") — if they can't picture the change, it's not feedback
- [ ] Do not save it for the review — feedback works when it's timely and low-stakes, not stockpiled

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description says to use the skill when asked to "give feedback" or "write a feedback note," which are common, everyday phrases that can arise in many contexts. It does not provide clearer trigger boundaries, exclusions, or negative examples to distinguish when this skill should activate versus when a general writing or coaching skill should be used instead.

Content

No source excerpt is available for this finding.