Back to skill

Security audit

Claim-to-Source Auditor

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign claim-to-source-auditor skill with no AIG findings and two low-probability, purpose-aligned Skillspector findings; overall confidence is medium because the scan was partial.

The verdict is benign, but benign does not mean risk-free. Skillspector scanned the one reported Markdown component, while overall analysis completeness is marked partial because a local path-like reference could not be resolved; consider that missing reference when deciding whether to install.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

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 159)May include surrounding context.

md
- A direct quote in an article that cannot be found in the reported source is a P0, even if the surrounding story is true.
- Near-miss numbers are still mismatches. An audit that reports 5810 when the source says 5817 must flag the difference.
- Cross-platform periods are high-risk. If one version reads "2024" and the other "2025", the different year is an error, not a paraphrase.
- Regulatory documents exist in specific jurisdictions. Never write "FDA, EU MDR, and China's regulations all say the same thing" without checking the governing text.

## Failure handling

The skill mandates Chinese-language verdict labels without offering a language choice.

Low
Category
Output Handling
Confidence
90% confidence
Finding

The workflow requires assigning Chinese verdict labels, which are also mandated in the report summary at line 133; line 112 similarly requires Chinese cross-platform comparison labels. No user opt-in, language-selection mechanism, or justified locale restriction is provided, even though the skill supports multilingual articles.

Content

No source excerpt is available for this finding.