complexity-assessment

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted user-provided task descriptions.
  • Ingestion points: The skill ingests and analyzes a user's task description to determine complexity scores and rationale (File: SKILL.md).
  • Boundary markers: No specific delimiters or "ignore instructions within data" warnings are defined for the input task description.
  • Capability inventory: The skill utilizes MCP tools for persistent memory storage and retrieval, including mcp__contextd__memory_record and mcp__contextd__memory_search (File: SKILL.md).
  • Sanitization: No explicit sanitization or validation of the input task description is mentioned before it is processed or recorded to memory.
  • [SAFE]: No hardcoded credentials, malicious network operations, or unauthorized privilege escalation commands were detected in the skill content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 06:39 PM