project-docs-sync

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill automatically propagates changes from source documentation files to other project documents, creating a surface for indirect prompt injection.
  • Ingestion points: Reads content from markdown files within the project-management/ directory, which may contain untrusted user input or external data.
  • Boundary markers: Absent. The logic does not define clear delimiters or specific instructions to the agent to ignore potentially malicious embedded instructions within the document content being processed.
  • Capability inventory: Uses the Write and Edit tools to modify project files (e.g., ARCHITECTURE.md, SPECIFICATIONS.md).
  • Sanitization: Absent. The current implementation relies on keyword-based classification and does not explicitly sanitize or escape the content being moved between files.
  • [SAFE]: No hardcoded credentials, malicious network operations, or unauthorized privilege escalation attempts were detected. The use of local state storage in .meta/last-sync.json is a standard practice for tracking sync status.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 01:12 PM
Security Audit — agent-trust-hub — project-docs-sync