document-review

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes document content that can contain adversarial instructions designed to hijack the agent's review logic or influence the sub-agents dispatched for simulations.
  • Ingestion points: Document content retrieved from file paths or docs/ directory (SKILL.md, Step 1).
  • Boundary markers: No delimiters or ignore instructions are provided to isolate the untrusted document content.
  • Capability inventory: The agent is authorized to modify files (Step 6) and spawn sub-agents (Step 7), creating a path for automated exploitation if an injected instruction is obeyed.
  • Sanitization: No validation or sanitization of document content is performed prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 04:45 PM