Back to skill

Security audit

Intent-Engineering

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent skill-design framework, but it asks to broadly govern agent behavior and includes unsafe workflow condition evaluation code.

Review before installing. This skill may be acceptable if you specifically want a broad governance framework for building multiple related skills, but do not run its orchestrator on untrusted workflow configurations unless the eval-based condition handling is removed. Require explicit user approval for scope expansion, logging, recursive framework updates, and any changes to existing skills.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:7
Finding

Skill Instructions Attempt to Govern and Redirect Agent Behavior

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/orchestrator.py:445
Finding

Arbitrary Python Code Execution Through Workflow Condition Evaluation

Content
View full analysis
bool: """Evaluate a condition string (simplified).""" # In production, use a safer evaluation method try: # Replace references with actual values eval_str = condition for step_id, result in step_results.items(): eval_str = eval_str.replace( f"steps[{step_id}].outputs", json.dumps(result.outputs) ) return eval(eval_str) except Exception as e: self.logger.warning(f"Failed to evaluate condition: {e}") return False ``` ### Technical Analysis `execute_workflow()` accepts a workflow configuration dictionary and forwards every conditional step's `condition` string to `_evaluate_condition()`. That method performs textual substitution for step-output references and then passes the resulting string directly to Python's unrestricted `eval()`. The substitution operation is not a security boundary. A condition does not need to contain a `steps[...]` reference and can directly use Python built-ins, function calls, attribute traversal, imports, and arbitrary expressions. Because `eval()` is invoked without restricted globals or locals, the evaluated expression inherits access to Python built-ins, including `__import__`. A malicious condit ...[truncated 2205 chars]
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (13)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

This finding indicates the skill may perform concrete runtime orchestration, file access, registration/invocation of async callables, and dynamic condition evaluation via eval while presenting itself as a high-level framework. That combination is high risk because hidden execution/orchestration capability—especially with eval—can enable arbitrary code execution, unsafe workflow routing, or policy bypass under the cover of a benign-seeming meta-skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

This finding indicates the skill may perform concrete runtime orchestration, file access, registration/invocation of async callables, and dynamic condition evaluation via eval while presenting itself as a high-level framework. That combination is high risk because hidden execution/orchestration capability—especially with eval—can enable arbitrary code execution, unsafe workflow routing, or policy bypass under the cover of a benign-seeming meta-skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

This finding indicates the skill may perform concrete runtime orchestration, file access, registration/invocation of async callables, and dynamic condition evaluation via eval while presenting itself as a high-level framework. That combination is high risk because hidden execution/orchestration capability—especially with eval—can enable arbitrary code execution, unsafe workflow routing, or policy bypass under the cover of a benign-seeming meta-skill.

Content

No source excerpt is available for this finding.

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · references/ecosystem_governance.md (reported line 245)May include surrounding context.

md
1. **Pause:** Stop deploying new versions; consider limiting rollout
2. **Investigate:** Deep dive into decision logs to understand the misalignment
3. **Root Cause Analysis:** Determine why the misalignment occurred
4. **Redesign:** Update skill logic, boundaries, or values to fix the issue
5. **Test:** Validate changes with integration tests and staging deployment
6. **Communicate:** Notify stakeholders of the issue and fix
7. **Monitor:** Increase monitoring frequency for the updated skill

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The conditional workflow feature executes arbitrary Python expressions from dynamic configuration, giving workflow authors code-execution capability inside the orchestration runtime. In a meta-orchestration skill that coordinates many other skills and their data, this is especially dangerous because the orchestrator likely has access to sensitive inputs, outputs, files, and credentials.

Content

No source excerpt is available for this finding.

eval() call detected

High
Category
Dangerous Code Execution
Confidence
99% confidence
Finding

The orchestrator evaluates workflow conditions with Python's eval() after only performing string replacement on step outputs. If workflow configuration or referenced outputs are attacker-controlled, this enables arbitrary code execution in the orchestrator process, which is far beyond the intended purpose of routing workflow steps.

Content

Scanner excerpt · scripts/orchestrator.py (reported line 459)May include surrounding context.

python
f"steps[{step_id}].outputs",
                    json.dumps(result.outputs)
                )
            return eval(eval_str)
        except Exception as e:
            self.logger.warning(f"Failed to evaluate condition: {e}")
            return False

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
81% confidence
Finding

The skill references concrete filesystem-backed resources such as references/... and scripts/orchestrator.py, which implies file-read capability, but it does not declare any tool scope or permissions boundary. In a meta-skill that influences how the agent operates, undeclared resource access reduces transparency and can cause the agent to access local files more broadly than users expect.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The statement that the agent uses this skill whenever the user asks it to build something creates an overbroad activation condition. For a meta-skill that can shape reasoning and potentially orchestrate other components, ambiguous always-on use increases the chance of unreviewed privilege expansion, unintended file access, or interference with unrelated tasks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The workflow trigger language is too broad, which can cause the skill to activate in contexts beyond its intended purpose. In a skill that describes itself as governing the agent and coordinating an ecosystem, ambiguous activation materially increases the blast radius of any unsafe behavior or hidden capability.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The comment acknowledges that a safer production approach is needed, but the live implementation still uses unsafe evaluation for conditions. This mismatch can create false confidence during review and deployment, increasing the likelihood that dangerous code reaches production unchanged.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This code evaluates workflow condition strings at runtime using eval, which is a safety-critical execution behavior in a code file. Although there is an internal comment noting safer evaluation should be used in production, there is no user-facing warning, confirmation, or explicit disclosure that workflow configuration can trigger arbitrary expression execution.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This manifest-style JSON says the skill "Listens for new tickets from helpdesk system" without specifying what counts as a qualifying event, source boundaries, or exclusion conditions. Because this file type is in scope for vague-trigger review, the activation condition is ambiguous and could allow unintended invocation on unrelated helpdesk events.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown template asks for a workflow trigger but provides only a broad example and no guidance on making trigger phrases specific or excluding common-language invocations. That can lead authors to define ambiguous triggers that cause unintended skill activation.

Content

No source excerpt is available for this finding.