brain-status

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by aggregating and displaying data from various local files.
  • Ingestion points: The skill reads metadata and content from pages/Projects___*.md (properties, Current Plan, Session Log), pages/Decisions.md, and pages/Meta.md.
  • Boundary markers: No delimiters or instructions are provided to the agent to treat the ingested file content as untrusted data or to ignore embedded instructions.
  • Capability inventory: The skill utilizes file globbing and targeted file reads. It also writes activity logs to skills/_shared/journey-log.md. No network or shell execution capabilities are present.
  • Sanitization: No sanitization, escaping, or validation of the content read from the markdown files is performed before it is presented to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 06:49 AM
Security Audit — agent-trust-hub — brain-status