paper-writing

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes research findings and technical data to generate paper drafts, which introduces a surface for indirect prompt injection if the source data contains hidden or malicious instructions.
  • Ingestion points: External research findings and collected technical documents processed during the /draft workflow.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted research data from the agent's drafting instructions.
  • Capability inventory: The skill utilizes the writer and verifier agents and performs file writes to the papers/ directory.
  • Sanitization: There is no evidence of input validation, escaping, or sanitization of the research findings before they are interpolated into the draft output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 01:46 AM
Security Audit — agent-trust-hub — paper-writing