ape-cut-fluff

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is text summarization and editing. It defines specific linguistic patterns to remove (hedging, filler words, redundant phrases) which are standard for an AI-assisted editor.
  • [EXTERNAL_DOWNLOADS]: The skill can download content from a URL using WebFetch or curl. However, the instructions specify that this is for the purpose of processing the text (e.g., blog posts or research papers) provided by the user, and it includes logic to strip non-content elements like navigation and footers. These are standard operations for a web-aware agent.
  • [COMMAND_EXECUTION]: The skill mentions using pdftotext or curl to process PDFs. These are standard utility commands for text extraction and do not indicate malicious intent or arbitrary command execution.
  • [DATA_EXPOSURE]: The skill reads files from disk if a path is provided. It explicitly avoids overwriting original files, instead creating a new file with a -cut suffix, which is a safety best practice. It does not attempt to access sensitive system directories or credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 11:56 AM
Security Audit — agent-trust-hub — ape-cut-fluff