Back to skill

Security audit

资料蒸馏为可用问答

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently creates source-backed FAQs from selected documents, with clearly optional aimeGeo content creation and user-requested publishing.

Choose a source folder containing only intended materials, and protect generated indexes because they include original text. Before choosing aimeGeo continuation, review derived content for confidential information and confirm the destination and publishing accounts. The optional renderer uses Chinese headings.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
Findings (7)

Env Variable Harvesting

High
Category
Data Exfiltration
Confidence
60% confidence
Finding

Code enumerates, copies, or searches environment variables for secrets. Bulk environment access can collect credentials unrelated to the skill's stated purpose.

Content

Scanner excerpt · scripts/self_test.py (reported line 407)May include surrounding context.

python
completed = subprocess.run([sys.executable, str(package / "scripts" / "knowledge.py"), "check",
                                    "--sources", str(package / "input"), "--index", str(package / "index.json"),
                                    "--bundle", str(package / "bundle.json")], cwd=elsewhere,
                                   env={**os.environ, "PYTHONDONTWRITEBYTECODE": "1"},
                                   capture_output=True, text=True, timeout=30)
        self.assertEqual((completed.returncode, completed.stderr), (0, ""))
        self.assertEqual(json.loads(completed.stdout)["questions"], 5)

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

The workflow saves source-derived tutorials and images to aimeGeo without a privacy warning.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow instructs the agent to create content from project materials and save the resulting tutorial and images in aimeGeo. It does not warn that source-derived information will be stored in that service or ask the user to check for confidential content; the instruction not to publish does not address this separate disclosure risk.

Content

No source excerpt is available for this finding.

The renderer forces Chinese-language headings, status labels, and explanatory text without a user-selectable locale.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The exported FAQ and issue report always contain Chinese headings and boilerplate, regardless of the user's language or the source material. This file provides no language opt-in, locale selection, or documented regional justification for that restriction.

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 404)May include surrounding context.

python
(package / "index.json").write_text(json.dumps(self.index), encoding="utf-8")
        elsewhere = self.work / "different-working-directory"
        elsewhere.mkdir()
        completed = subprocess.run([sys.executable, str(package / "scripts" / "knowledge.py"), "check",
                                    "--sources", str(package / "input"), "--index", str(package / "index.json"),
                                    "--bundle", str(package / "bundle.json")], cwd=elsewhere,
                                   env={**os.environ, "PYTHONDONTWRITEBYTECODE": "1"},

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 32)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