Security risk report for @forgecat/openai_skills_pdf v0.0.10
Source Integrity
Low
Profile is attributed to OpenAI's official skills repository with a specific commit hash and Apache-2.0 license.
Metadata (author, original repository, version) is transparent and traceable to a legitimate upstream source.
Agent Intent
Low
Content describes legitimate PDF processing workflows using well-known, standard Python libraries (reportlab, pdfplumber, pypdf) and system tools (Poppler/pdftoppm).
No instructions to read credentials, exfiltrate data, ignore system prompts, or execute remote payloads.
Guidance on dependency installation and rendering is standard practice, not poisoning — recommends widely-used, unmodified packages from official sources.
Details
Evidence
'prefer visual checks by rendering pages (Poppler) and use Python tools such as `reportlab`, `pdfplumber`, and `pypdf`'
No tool definitions or hooks declared in the profile.
Skill is purely instructional guidance for the agent on when and how to use PDF libraries — does not request shell, file_write, file_delete, or other high-risk permissions.
Authority is scoped to PDF processing workflows and matches the stated function.
Details
Evidence
'(none declared)' in the tools section
No alwaysApply rules or glob patterns requesting broad filesystem or shell access
MCP Risk
Low
No MCP servers defined in the profile.
No hidden instructions in tool descriptions or arbitrary binary execution.
Profile is purely markdown guidance with no server configuration.
ForgeCat