dotnet-core-expert

AdvisoryAudited by Static analysis on May 9, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

NoteHigh Confidence

ASI02: Tool Misuse and Exploitation

What this means

The skill may guide an agent toward substantial project or deployment changes if the surrounding agent has those tools.

Why it was flagged

If paired with file, database, or cloud tools, these broad workflow steps could modify a codebase or deployment environment. This is aligned with the .NET expert purpose, but the artifacts do not define approval boundaries.

Skill content

Implementation approach:
- Create projects
- Implement services
- Build APIs
- Setup database
- Add authentication
- Write tests
- Optimize performance
- Deploy application

Recommendation

Require user review before applying generated code, changing databases, configuring CI/CD, or deploying to cloud/Kubernetes environments.

NoteHigh Confidence

ASI09: Human-Agent Trust Exploitation

What this means

A user could mistakenly trust unverified completion, performance, or deployment claims.

Why it was flagged

The canned delivery message contains specific test coverage, performance, and deployment claims. If treated literally rather than as an example, it could overstate what was actually built, tested, benchmarked, or deployed.

Skill content

Delivery notification:
".NET application completed. Built 12 microservices with 45 APIs achieving 83% test coverage. Native AOT compilation reduces startup to 180ms and memory by 65%. Deployed to Kubernetes with auto-scaling."

Recommendation

Treat such completion text as a template only, and ask the agent to cite actual test results, benchmark output, deployment logs, or changed files.