personal-workspace-router

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by reading and processing content from local files (AGENTS.md, MEMORY.md) which may contain instructions from untrusted sources or repository contexts.
  • Ingestion points: Local filesystem reads of AGENTS.md, MEMORY.md, DECISIONS.md, and ROUTING-LOG.md within the domains/ directory structure.
  • Boundary markers: Absent. The instructions do not specify delimiters or constraints to ensure the agent ignores instructions potentially embedded within the data it reads.
  • Capability inventory: Filesystem read/write access and local directory management.
  • Sanitization: None. There is no logic provided to sanitize or validate the content ingested from the local workspace files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:33 PM
Security Audit — agent-trust-hub — personal-workspace-router