check-completeness

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests markdown data from documentation source and output directories, creating a surface for indirect prompt injection where malicious instructions in those files could influence agent behavior.
  • Ingestion points: SKILL.md (Step 1) loads source files from data/markdown/ and output files from docs/src/content/docs/.
  • Boundary markers: The instructions do not establish delimiters or provide warnings to ignore embedded commands in the processed data.
  • Capability inventory: The skill possesses file-writing capabilities through the 'Repair' phase in Step 5.
  • Sanitization: There is no evidence of sanitization or filtering applied to the documentation content before it is processed or written back to the file system.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:03 PM
Security Audit — agent-trust-hub — check-completeness