chakra-and-energy-systems-expert

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill instructs the agent to perform research from external, untrusted sources (Wikipedia, Arxiv, web searches) to validate and update its core guidance. This creates a surface for indirect prompt injection.
  • Ingestion points: Workflow defined in modules/research-checklist.md (e.g., Step 2: 'Run targeted web searches').
  • Boundary markers: Absent; the skill does not provide instructions to delimit or ignore instructions within external data.
  • Capability inventory: The skill utilizes agent tools such as adn_skills('distill_from_wikipedia', ...) for data processing.
  • Sanitization: Absent; no validation or sanitization steps are defined for external content.
  • [NO_CODE]: The skill consists entirely of Markdown documentation and instructions with no executable scripts or binary files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 05:38 PM
Security Audit — agent-trust-hub — chakra-and-energy-systems-expert