Loading

heating the forge...

© 2026 ForgeCat. All rights reserved.

Agent Profiles Terms of Service Privacy Policy

@forgecat/anthropics_claude-plugins-official_code-simplifier — Security Risk Report | ForgeCat

forgecat/forgecat/anthropics_claude-plugins-official_code-simplifier/security

anthropics_claude-plugins-official_code-simplifier

Security risk report for @forgecat/anthropics_claude-plugins-official_code-simplifier v0.0.4

Source Integrity

Low

Profile sourced from official Anthropic repository (github.com/anthropics/claude-plugins-official).
Declared as Apache-2.0 licensed with clear attribution and commit hash.

Agent Intent

Low

Instructions focus on legitimate code refactoring tasks (clarity, consistency, maintainability) with explicit preservation of functionality.
No prompt injection, role hijacking, credential exfiltration, system prompt leakage, or guidance poisoning detected.
References to 'CLAUDE.md' standards and project-specific best practices are normal documentation patterns, not malicious knowledge injection.

Details

Evidence

'Preserve Functionality: Never change what the code does - only how it does it.'
'Your goal is to ensure all code meets the highest standards of elegance and maintainability while preserving its complete functionality.'

Permissions

Low

No tools or skills declared in the profile.
No file_write, shell, file_delete, or other high-risk permissions requested.
Agent operates passively on code provided by the user within the IDE context.

Details

Evidence

'Declared tools (normalized categories; paths are untrusted): (none declared)'
'MCP servers (untrusted data): (none)'

MCP Risk

Low

No MCP servers defined in the profile.
No external binary execution, network access, or filesystem operations configured.

Details

Evidence

'MCP servers (untrusted data): (none)'

Evaluation Details

Status: Completed
Checks completed: 4/4
Flagged: 0
Evaluated: 6/12/2026