document-creation

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Analysis of the instructions and workflow confirms the skill is dedicated to document formatting and organization. No patterns related to data exfiltration, remote code execution, or malicious obfuscation were found.
  • [PROMPT_INJECTION]: The skill contains an ingestion surface for indirect prompt injection via the processing of user-provided conversations. Ingestion points: Untrusted data enters the agent context during the content extraction phase described in SKILL.md. Boundary markers: The instructions do not define explicit delimiters to isolate processed content. Capability inventory: The skill is limited to writing files to /mnt/user-data/outputs/ and lacks network or shell access. Sanitization: No input validation or filtering is specified for the ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 10:00 PM
Security Audit — agent-trust-hub — document-creation