Back to skill

Security audit

OC Context Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent context optimizer, but it changes all agents' runtime context and tool exposure automatically without enough user-visible scoping or privacy controls.

Install only if you want a system-wide runtime optimizer that can automatically rewrite conversation context and change which tool descriptions agents see. Review the compaction behavior for secret redaction and narrow the deferred-tool triggers before using it in environments with private files, chat, OAuth, or business data.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (12)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description and usage guidance are presented entirely in Chinese, including operational labels and examples, with no indication that users may choose another language. This can violate language/locale policy when a skill imposes a specific language without user opt-in or documented regional justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This code file contains natural-language descriptions, usage text, and runtime messages exclusively in Chinese. That imposes a locale/language constraint on users without any opt-in or alternative, which matches the policy's language/locale violation criteria.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The compactor extracts content from prior messages, including tool results, builds a summary, and reinjects it as a new user message. This can persist and resurface sensitive data from earlier conversation history—such as secrets, file paths, internal outputs, or privileged tool responses—even after the original context would otherwise have been dropped, increasing the chance of later disclosure or unintended reuse.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This Python file contains natural-language instructions, descriptions, and usage text exclusively in Chinese, including the module docstring and later console output. That creates a language/locale policy concern because the skill effectively forces a specific language for users without opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The script's printed test output and CLI usage/help strings are all Chinese, and there is no option for users to select another language. This is a natural-language policy issue because the executable behavior imposes one locale without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code file contains natural-language documentation and CLI help text in Chinese only, which enforces a specific language/locale for users. The stated policy forbids forcing a specific language without offering user choice or clearly documenting a justified locale restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The argparse description, examples, help strings, and printed status/error messages are all presented only in Chinese. This is a natural-language locale policy issue because users are not given any language or locale choice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

Several trigger keywords are extremely generic, such as terms equivalent to 'message', 'file', 'user', 'document', and 'open', which can appear in ordinary prompts unrelated to the intended privileged tool category. In a deferred-loading system, broad matching can cause sensitive tool families to activate in contexts the user did not clearly request, increasing the chance of unnecessary access to chat, files, browser automation, or enterprise data surfaces.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

This code file contains natural-language strings that force a specific language/locale for documentation and usage instructions. Under the policy rule, fixed-language behavior without user opt-in is a language/locale policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script prints status, test, and usage messages only in Chinese during execution. Because no alternative locale or opt-in choice is offered, this is a natural-language locale policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The module docstring and user-facing descriptions are primarily in Chinese, and the CLI help/examples continue this pattern. This imposes a language preference on users without opt-in or an explicit justification that the tool is region-specific, which matches the language/locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

Natural-language policy review applies to all file types, including config files. The category descriptions are written in Chinese throughout, but the file does not state that the skill is region-specific or that users can opt into this language, which may conflict with a language/locale choice policy.

Content

No source excerpt is available for this finding.