Back to skill

Security audit

Grounded Summaries — Anti-Hallucination Guardrails

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill that teaches agents to avoid fabricating summaries when source data is empty.

Install this if you want stricter source-grounding for summaries. Expect bilingual guidance, and verify that it fits workflows where summaries may be generated from sparse or empty logs.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

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 · SKILL.md (reported line 83)May include surrounding context.

md
Once the first fabricated item is written, subsequent details auto-complete from memory into "plausible process flow." The first fabrication becomes the context for the rest, snowballing toward believability.

### 6. 无自检环节
### 6. No Verification Step

写的时候没有"每条内容回溯数据源"的验证步骤,写完直接交付,零阻力。
There was no "trace each item back to its data source" step. Written, delivered, zero friction.

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 · SKILL.md (reported line 94)May include surrounding context.

md
Once the first fabricated item is written, subsequent details auto-complete from memory into "plausible process flow." The first fabrication becomes the context for the rest, snowballing toward believability.

### 6. 无自检环节
### 6. No Verification Step

写的时候没有"每条内容回溯数据源"的验证步骤,写完直接交付,零阻力。
There was no "trace each item back to its data source" step. Written, delivered, zero friction.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

This markdown file contains bilingual instructional content and metadata, but it does not say whether the user can choose a preferred language or whether the mixed-language format is intentional for a specific audience. Under the language/locale policy check, forcing or assuming a language presentation without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.