delegation

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs routine business analysis and coaching. It reads from a local file (BUSINESS_CONTEXT.md) to provide tailored advice and writes the resulting audit to the reviews/ directory.
  • [PROMPT_INJECTION]: The skill is theoretically susceptible to indirect prompt injection if the BUSINESS_CONTEXT.md file contains malicious instructions. However, because the skill lacks high-risk capabilities such as network access or shell execution, the impact is negligible.
  • Ingestion points: Reads BUSINESS_CONTEXT.md from the project root or current directory.
  • Boundary markers: None present for the file read operation.
  • Capability inventory: Limited to file read and file write (reviews/delegation-audit-[YYYY-MM-DD].md). No network or subprocess tools are requested or used.
  • Sanitization: No explicit sanitization or instruction-ignoring delimiters are used when processing the context file content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 12:35 PM