ClawHub
Back to skill

Security audit

data-flow-review

Security checks for vulnerabilities and agentic risk

Overview

This is a plain code-review guidance skill with no executable code, persistence, network access, or hidden authority.

Install this if you want Codex to perform stricter data-flow-oriented code reviews. Expect it to read relevant code paths when invoked, but the skill itself does not install code, run commands, persist data, or request credentials.

A.I.G

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

SkillSpector

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 (3)

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 194)May include surrounding context.

md
## Anti-Patterns

- Do not judge a field only by its interface name.
- Do not stop tracing after the first correct local use.
- Do not assume a later overwrite makes earlier wrong writes harmless.
- Do not ignore cancel, retry, refresh, resume, or failure branches.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The natural-language description is written entirely in Chinese while the rest of the skill is in English, and the file does not state that the skill is region-specific or that users may choose their preferred language. This can violate language/locale policy by implicitly forcing a specific language without opt-in.

Content

No source excerpt is available for this finding.

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 198)May include surrounding context.

md
- Do not stop tracing after the first correct local use.
- Do not assume a later overwrite makes earlier wrong writes harmless.
- Do not ignore cancel, retry, refresh, resume, or failure branches.
- Do not accept fallback expressions as safe without checking semantic equivalence.
- Do not review only one layer when the bug is about cross-layer drift.
- Do not summarize architecture before identifying concrete correctness risks.

Static analysis

No suspicious patterns detected.