consulting-analysis

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill is implemented entirely in Markdown and provides instructions for the AI agent to follow. It does not contain any Python code, Node.js packages, or shell scripts.
  • [PROMPT_INJECTION]: The skill describes a process that ingests external data summaries and search results, creating a surface for indirect prompt injection.
  • Ingestion points: Phase 2 takes external inputs such as 'Data Summary' and 'External Search Findings' from other agents (e.g., deep-research).
  • Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the processed data.
  • Capability inventory: This skill is focused on text and report generation; it does not have capabilities for command execution, file system modification, or outbound network calls.
  • Sanitization: No sanitization or validation logic is defined for the external data before it is integrated into the narrative report.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 10:49 PM