ClawHub
Back to skill

Security audit

小说审稿评分

Security checks for vulnerabilities and agentic risk

Overview

The skill reviews user-provided manuscripts and optionally saves reports through a clearly disclosed, narrowly scoped workflow.

Provide only manuscript material you intend the host AI to process. Saved reviews include quotations, so choose an appropriate new output directory. The helper checks structure and formatting, not whether the review accurately reflects the manuscript. The scanner's unresolved report filenames are documented generated outputs, not missing dependencies.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)

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

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.

Dynamic import via __import__()

Medium
Category
Dangerous Code Execution
Confidence
75% confidence
Finding

Dynamic import() can load arbitrary modules at runtime, bypassing static analysis and potentially importing malicious code.

Content

Scanner excerpt · tests/test_review.py (reported line 102)May include surrounding context.

python
with tempfile.TemporaryDirectory() as tmp:
            inp = Path(tmp) / "review.json"; inp.write_text(json.dumps(self.sample), encoding="utf-8")
            out = Path(tmp) / "out"; out.mkdir(); (out / "review.md").write_text("keep", encoding="utf-8")
            old_argv = __import__("sys").argv
            try:
                __import__("sys").argv = ["self_test.py", "render", "--input", str(inp), "--output", str(out)]
                self.assertEqual(module.main(), 1)

Dynamic import via __import__()

Medium
Category
Dangerous Code Execution
Confidence
75% confidence
Finding

Dynamic import() can load arbitrary modules at runtime, bypassing static analysis and potentially importing malicious code.

Content

Scanner excerpt · tests/test_review.py (reported line 104)May include surrounding context.

python
out = Path(tmp) / "out"; out.mkdir(); (out / "review.md").write_text("keep", encoding="utf-8")
            old_argv = __import__("sys").argv
            try:
                __import__("sys").argv = ["self_test.py", "render", "--input", str(inp), "--output", str(out)]
                self.assertEqual(module.main(), 1)
            finally:
                __import__("sys").argv = old_argv

Dynamic import via __import__()

Medium
Category
Dangerous Code Execution
Confidence
75% confidence
Finding

Dynamic import() can load arbitrary modules at runtime, bypassing static analysis and potentially importing malicious code.

Content

Scanner excerpt · tests/test_review.py (reported line 107)May include surrounding context.

python
__import__("sys").argv = ["self_test.py", "render", "--input", str(inp), "--output", str(out)]
                self.assertEqual(module.main(), 1)
            finally:
                __import__("sys").argv = old_argv
            self.assertEqual((out / "review.md").read_text(encoding="utf-8"), "keep")
            self.assertFalse((out / "review.json").exists())

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