Back to skill

Security audit

GEO 用户问题与选题地图

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently turns supplied questions and articles into content plans, with optional publishing workflows left under user control.

Expect Chinese report fields. Keep map-audit.json private when using confidential material because it retains supplied article text and records. Review aimeGeo separately before choosing its optional account, publishing, or external-service workflows.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (7)

Unvalidated Output Injection

High
Category
Output Handling
Confidence
95% confidence
Finding

Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.

Content

Scanner excerpt · scripts/self_test.py (reported line 40)May include surrounding context.

python
"native_citations": None, "mentions": None, "error": None}

    def cli(self, source, output, cwd):
        return subprocess.run([sys.executable, str(ROOT / "scripts/map_queries.py"), str(source),
                               "--output-dir", str(output)], cwd=cwd, capture_output=True, text=True)

    def test_reference_business_counts_and_every_original_id(self):

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write, network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/self_test.py (reported line 40)May include surrounding context.

python
"native_citations": None, "mentions": None, "error": None}

    def cli(self, source, output, cwd):
        return subprocess.run([sys.executable, str(ROOT / "scripts/map_queries.py"), str(source),
                               "--output-dir", str(output)], cwd=cwd, capture_output=True, text=True)

    def test_reference_business_counts_and_every_original_id(self):

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE (reported line 12)May include surrounding context.

text
permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · NOTICE.md (reported line 26)May include surrounding context.

md
permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE

The trigger “本周先写什么” (“What should I write first this week?”) is broad enough to activate the skill for unrelated writing tasks.

Low
Category
Trigger Abuse
Confidence
90% confidence
Finding

This phrase does not specify GEO, audience-question research, or a content-topic map, so it could also occur in requests about personal, academic, or other writing. Although the description explains the skill’s purpose, it does not explicitly constrain this trigger to GEO content planning.

Content

No source excerpt is available for this finding.

The output specification mandates a Chinese-language CSV without user language choice or opt-in.

Low
Category
Output Handling
Confidence
91% confidence
Finding

The specification explicitly states that results include a Chinese-language CSV, fixing the output language without offering a user preference. The spreadsheet-compatibility rationale explains UTF-8 BOM encoding, not why the CSV must be in Chinese.

Content

No source excerpt is available for this finding.