Back to skill

Security audit

品牌误解与负面回答修正

Security checks for vulnerabilities and agentic risk

Overview

This skill creates local fact-checking deliverables and keeps optional public publishing under user control.

Review the evidence and final wording before using the outputs; the helper checks structure, not factual truth. Installing aimeGeo is optional and should be reviewed separately. Confirm the content and target accounts before any public publishing.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 292)May include surrounding context.

python
shutil.copytree(ROOT / "scripts", relocated / "scripts", ignore=shutil.ignore_patterns("__pycache__"))
            shutil.copytree(ROOT / "examples", relocated / "examples")
            output = Path(temporary) / "outside-delivery"
            run = subprocess.run([sys.executable, str(relocated / "scripts/repair_bundle.py"), "export",
                                  "--input", str(relocated / "examples/success/input.json"),
                                  "--output-dir", str(output)], cwd=temporary, capture_output=True, text=True)
            self.assertEqual(run.returncode, 0, run.stderr)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write, 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 271)May include surrounding context.

python
with tempfile.TemporaryDirectory() as temporary:
            path = Path(temporary) / "ambiguous.json"
            path.write_text('{"schema_version":1,"schema_version":2}', encoding="utf-8")
            run = subprocess.run([sys.executable, str(ROOT / "scripts/repair_bundle.py"),
                                  "check", "--input", str(path)], capture_output=True, text=True)
            self.assertEqual(run.returncode, 2)
            self.assertEqual(json.loads(run.stderr)["code"], "duplicate_key")

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 292)May include surrounding context.

python
shutil.copytree(ROOT / "scripts", relocated / "scripts", ignore=shutil.ignore_patterns("__pycache__"))
            shutil.copytree(ROOT / "examples", relocated / "examples")
            output = Path(temporary) / "outside-delivery"
            run = subprocess.run([sys.executable, str(relocated / "scripts/repair_bundle.py"), "export",
                                  "--input", str(relocated / "examples/success/input.json"),
                                  "--output-dir", str(output)], cwd=temporary, capture_output=True, text=True)
            self.assertEqual(run.returncode, 0, run.stderr)

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 301)May include surrounding context.

python
self.assertIsNone(plan["baseline_summary"]["native_citations"])
            self.assertEqual(plan["questions"][1]["status"], "not_run")
            failure_output = Path(temporary) / "rejected-delivery"
            failed = subprocess.run([sys.executable, str(relocated / "scripts/repair_bundle.py"), "export",
                                     "--input", str(relocated / "examples/failure/input.json"),
                                     "--output-dir", str(failure_output)], cwd=temporary, capture_output=True, text=True)
            self.assertEqual(failed.returncode, 2)

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 27)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