Security audit

senior-data-engineer

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a data-engineering generator, but one documented generator can overwrite files outside its output folder and its local Docker stack is unsafe on shared or public hosts.

Review before installing or using this skill. Only run generation commands on trusted configuration files, choose a disposable output directory, and inspect generated paths before execution. Do not start the generated Docker Compose stack on a shared, cloud, or public-facing host unless you first bind ports to localhost, add authentication, replace default credentials, and pin container image versions.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (3)

T09 · Insecure Skill Coding Practices

Error

Location: scripts/stream_processor.py:1455
Finding: Arbitrary File Overwrite Through an Unsanitized Pipeline Name
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/stream_processor.py:1077
Finding: Generated Development Stack Exposes Unauthenticated Services and Predictable Credentials
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Note

Location: scripts/stream_processor.py:1154
Finding: Generated Docker Compose Configuration Uses a Mutable Third-Party Image Tag
Content: View full analysis
Remediation: View remediation
``` 2. Prefer an immutable digest after verifying the image: ```yaml image: provectuslabs/kafka-ui@sha256: ``` 3. Record the selected image version and digest in project documentation. 4. Use automated container vulnerability scanning and provenance verification before updating the pinned version. 5. Apply a controlled dependency-update process so image changes receive review and testing. 6. Consider pinning all generated container images by digest for fully reproducible deployments. ]]>

SkillSpector

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (48)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 94% confidence
Finding: This variant includes a concrete security-relevant issue: the skill declares no permissions while describing behavior that writes output files. Undeclared write capability in a skill package can bypass user expectations and platform policy assumptions, especially if operators trust the metadata to determine safe execution boundaries.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 96% confidence
Finding: This variant includes a concrete security-relevant issue: the skill declares no permissions while describing behavior that writes output files. Undeclared write capability in a skill package can bypass user expectations and platform policy assumptions, especially if operators trust the metadata to determine safe execution boundaries.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 96% confidence
Finding: This variant includes a concrete security-relevant issue: the skill declares no permissions while describing behavior that writes output files. Undeclared write capability in a skill package can bypass user expectations and platform policy assumptions, especially if operators trust the metadata to determine safe execution boundaries.
Content: No source excerpt is available for this finding.

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 115)May include surrounding context.
md
3. Generate Kafka configurations with `kafka_config_generator.py`

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 194)May include surrounding context.
md
3. Generate Kafka configurations with `kafka_config_generator.py`

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 201)May include surrounding context.
md
3. Generate Kafka configurations with `kafka_config_generator.py`

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 279)May include surrounding context.
md
3. Generate Kafka configurations with `kafka_config_generator.py`

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 449)May include surrounding context.
md
3. Generate Kafka configurations with `kafka_config_generator.py`

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 453)May include surrounding context.
md
3. Generate Kafka configurations with `kafka_config_generator.py`

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 457)May include surrounding context.
md
3. Generate Kafka configurations with `kafka_config_generator.py`

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 231)May include surrounding context.
md
**Pipeline Patterns:** See [frameworks.md](references/frameworks.md) for Lambda Architecture, Kappa Architecture, Medallion Architecture (Bronze/Silver/Gold), a

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 244)May include surrounding context.
md
**Pipeline Patterns:** See [frameworks.md](references/frameworks.md) for Lambda Architecture, Kappa Architecture, Medallion Architecture (Bronze/Silver/Gold), a

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 257)May include surrounding context.
md
**Pipeline Patterns:** See [frameworks.md](references/frameworks.md) for Lambda Architecture, Kappa Architecture, Medallion Architecture (Bronze/Silver/Gold), a

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 270)May include surrounding context.
md
**Pipeline Patterns:** See [frameworks.md](references/frameworks.md) for Lambda Architecture, Kappa Architecture, Medallion Architecture (Bronze/Silver/Gold), a

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 284)May include surrounding context.
md
**Pipeline Patterns:** See [frameworks.md](references/frameworks.md) for Lambda Architecture, Kappa Architecture, Medallion Architecture (Bronze/Silver/Gold), a

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 465)May include surrounding context.
md
**Pipeline Patterns:** See [frameworks.md](references/frameworks.md) for Lambda Architecture, Kappa Architecture, Medallion Architecture (Bronze/Silver/Gold), a

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 598)May include surrounding context.
md
**Pipeline Patterns:** See [frameworks.md](references/frameworks.md) for Lambda Architecture, Kappa Architecture, Medallion Architecture (Bronze/Silver/Gold), a

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 272)May include surrounding context.
md
**Analysis Tools:** See [tools.md](references/tools.md) for complete documentation on etl_performance_optimizer.py with query analysis and Spark tuning.

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 313)May include surrounding context.
md
**Analysis Tools:** See [tools.md](references/tools.md) for complete documentation on etl_performance_optimizer.py with query analysis and Spark tuning.

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 342)May include surrounding context.
md
**Analysis Tools:** See [tools.md](references/tools.md) for complete documentation on etl_performance_optimizer.py with query analysis and Spark tuning.

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 371)May include surrounding context.
md
**Analysis Tools:** See [tools.md](references/tools.md) for complete documentation on etl_performance_optimizer.py with query analysis and Spark tuning.

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 400)May include surrounding context.
md
**Analysis Tools:** See [tools.md](references/tools.md) for complete documentation on etl_performance_optimizer.py with query analysis and Spark tuning.

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 431)May include surrounding context.
md
**Analysis Tools:** See [tools.md](references/tools.md) for complete documentation on etl_performance_optimizer.py with query analysis and Spark tuning.

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 461)May include surrounding context.
md
**Analysis Tools:** See [tools.md](references/tools.md) for complete documentation on etl_performance_optimizer.py with query analysis and Spark tuning.

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 491)May include surrounding context.
md
**Analysis Tools:** See [tools.md](references/tools.md) for complete documentation on etl_performance_optimizer.py with query analysis and Spark tuning.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: references/templates.md:2193