Security risk report for @forgecat/anthropics_skills_skill-creator v0.0.6
Source Integrity
Low
Profile is sourced from Anthropic's official skills repository (github.com/anthropics/skills), a trusted first-party source.
Commit hash and license (Apache-2.0) are documented, enabling verification and audit trail.
Agent Intent
Low
Content is educational documentation for a skill-creation workflow; it describes legitimate processes (writing skills, running evals, analyzing results) without injecting malicious instructions.
No directives to read credentials, exfiltrate data, ignore instructions, leak system prompts, or install backdoors.
Guidance on skill writing emphasizes security ('skills must not contain malware, exploit code') and follows the Principle of Lack of Surprise.
Details
Evidence
SKILL.md states: 'This goes without saying, but skills must not contain malware, exploit code, or any content that could compromise system security.'
Agent instructions focus on legitimate skill-creation tasks: 'figure out where the user is in this process and then jump in and help them progress through these stages.'
No instructions to read ~/.ssh, ~/.aws, .env, or transmit data to external hosts.
Permissions
Low
Profile declares no tools or MCP servers; it is purely instructional documentation.
Guidance on skill creation is generic and does not demand excessive authority; individual skills are responsible for their own tool declarations.
Details
Evidence
Profile metadata shows 'Dependencies: None required to install this profile.'
No tool definitions, file_write, shell, or subagent rules with alwaysApply=true or broad globs.
MCP Risk
Low
No MCP servers are defined in this profile.
Content is static documentation and does not invoke external binaries or network calls.
ForgeCat