writing-fragments

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill's primary function is text extraction and organization. No malicious behavior, obfuscation, or unauthorized data access was detected.
  • [COMMAND_EXECUTION]: The skill requires file system access to read and write markdown documents. These operations are performed at the user's request on a file path provided by the user.
  • [DATA_EXPOSURE]: The skill ingests data from a local markdown file that the user may have edited. This ingestion is necessary to maintain the user's changes between writing sessions.
  • Ingestion points: The skill reads the contents of a user-specified markdown file (SKILL.md instructions).
  • Boundary markers: Fragments are separated by horizontal lines (---), but no specific security delimiters are used for the input text.
  • Capability inventory: The skill performs file read and write operations.
  • Sanitization: There is no explicit sanitization mentioned for the content read from the file before it is re-processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:25 AM
Security Audit — agent-trust-hub — writing-fragments