Back to skill

Security audit

SEO + GEO Audit

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent SEO and AI-visibility audit template with optional public web/search checks and no executable or persistent behavior.

Use this skill for website SEO/GEO audits. Expect it to inspect public pages and, if you configure SERPAPI_API_KEY, enrich findings with search-result data; do not provide private analytics or Search Console data unless you intend that extra context to be used.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (6)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 160)May include surrounding context.

md
- `Operator mode`
   - `Specialist mode`

## Output Rules

- If the user writes in Chinese, answer in Chinese unless asked otherwise.
- Always begin with a short executive summary.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description says to use the skill when the user asks for a "full SEO audit" or "wants one prioritized report," which are broad formulations that may overlap with many general website-review requests. It does not provide exclusion conditions or negative examples to distinguish this skill from other audit or analysis skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The language rules specify '优先中文' and further constrain terminology style, which creates a locale preference in the skill instructions. Under the policy, forcing or defaulting to a specific language without offering user choice can be a natural-language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The prompt example 'Give me an operator-style SEO GEO audit with P0, P1, and P2 actions' is phrased as a general request and does not require a URL, target scope, or explicit invocation boundary. In a manifest or README, this kind of broad example can contribute to ambiguous activation because it is unclear when a generic 'audit' request should invoke this specific skill versus other analysis skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The example 'Review this site for AI visibility, EEAT, and entity clarity' is descriptive but still broad enough to resemble ordinary consultation language. The README does not pair these examples with negative examples or explicit boundaries clarifying when this skill should or should not be selected.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The example phrase "Audit this homepage in boss mode" uses informal wording that does not itself identify the SEO/GEO domain and could collide with unrelated audit contexts. Because it is presented as a start phrase without accompanying limits, it weakens trigger specificity.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.