ClawHub
Back to skill

Security audit

python-code-pep8-style

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only PEP 8 style skill with no executable code, persistence, or hidden data access.

Install this if you want an agent to apply PEP 8 conventions during Python work. Be aware it may favor strict defaults such as 79-character lines, organized imports, conventional naming, and English comments unless your project or explicit instructions say otherwise.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description includes broad triggers such as writing, reviewing, refactoring, production-grade Python, and best practices, which can cause the skill to activate for general Python tasks well beyond formatting. That scope expansion can silently steer substantive code generation and review behavior under the banner of style guidance, increasing the chance that users receive prescriptive non-style changes they did not request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The instruction to write comments in English unless the author is "120% sure" of a narrow audience imposes a language policy without user consent. This can override user or project requirements, create exclusion or compliance issues in multilingual environments, and cause the skill to rewrite or reject otherwise acceptable documentation based on policy rather than security or correctness.

Content

No source excerpt is available for this finding.

Behavior Manipulation

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Subtle instructions detected that may alter agent decision-making or introduce hidden biases.

Content

Scanner excerpt · skill.md (reported line 1214)May include surrounding context.

md
operator.  However, it is best to implement all six operations so
  that confusion doesn't arise in other contexts.

- Always use a def statement instead of an assignment statement that binds
  a lambda expression directly to an identifier:

  .. code-block::

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 · skill.md (reported line 85)May include surrounding context.

md
which would also naturally be indented to 4 spaces.  This PEP takes no
explicit position on how (or whether) to further visually distinguish such
conditional lines from the nested suite inside the ``if``-statement.
Acceptable options in this situation include, but are not limited to:

.. code-block::
   :class: good

Static analysis

No suspicious patterns detected.