writing-shape

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted markdown files (the 'input pile') which could contain malicious instructions designed to influence the agent's behavior during the writing session.\n
  • Ingestion points: The skill reads a raw material markdown file and an article file provided by the user (SKILL.md).\n
  • Boundary markers: The instructions lack explicit boundary markers or delimiters to isolate untrusted content from the agent's instructions.\n
  • Capability inventory: The skill uses file read and write operations to perform its primary function.\n
  • Sanitization: There are no specific sanitization or validation steps mentioned, though the instructions to 'rework' and 'paraphrase' the material act as a natural linguistic filter.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 01:57 AM
Security Audit — agent-trust-hub — writing-shape