Security risk report for @forgecat/openai_skills_security-threat-model v0.0.10
Source Integrity
Low
Profile is sourced from OpenAI's official skills repository (https://github.com/openai/skills) with a specific commit hash and Apache-2.0 license.
Metadata is consistent and verifiable; no obfuscation or suspicious origin indicators.
Agent Intent
Low
Content is a legitimate security threat modeling skill that teaches AppSec methodology and best practices (evidence collection, trust boundary mapping, asset enumeration, attacker modeling).
No instructions to manipulate the AI, exfiltrate data, read credentials, hide instructions, or install malicious payloads.
Guidance on redacting secrets and grounding findings in evidence reflects security-conscious design, not poisoning.
Details
Evidence
'Never output secrets. If you encounter tokens/keys/passwords, redact them and only describe their presence and location.'
'Do not invent components, data stores, endpoints, flows, or controls. Every architectural claim must be backed by at least one Evidence anchor.'
Skill description: 'Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling.'
Permissions
Low
No tool definitions or MCP servers declared; the profile is purely instructional documentation for a threat modeling workflow.
Skill operates within the AI agent's native code analysis and reasoning capabilities (reading repo files, analyzing architecture, generating Markdown reports).
No shell, file_write, file_delete, or other high-risk tool categories requested.
Details
Evidence
'Dependencies: None'
'Declared tools: (none declared)'
'MCP servers: (none)'
MCP Risk
Low
No MCP servers are defined or referenced in the profile.
The skill relies on the agent's built-in code analysis and documentation generation, not external tool execution.
ForgeCat