domain-context

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized command executions were detected. The skill's instructions are focused on defining a collaborative protocol for domain knowledge documentation.
  • [EXTERNAL_DOWNLOADS]: The README file describes an installation process using npx skills add customware-ai/skills --skill domain-context. This references the vendor's own repository for deployment and is a standard procedure.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection by design as it ingests content from project-specific files. 1. Ingestion points: The skill reads .tasks/domain.md and files within docs/domain/ (referenced in SKILL.md). 2. Boundary markers: Absent; the instructions do not specify delimiters for the file content. 3. Capability inventory: The skill possesses no dangerous capabilities such as subprocess execution, network operations, or automated file writes; it only produces text-based update suggestions. 4. Sanitization: Absent. Because the skill lacks exploitable capabilities and uses a human-in-the-loop review process, this surface is considered safe.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:28 PM
Security Audit — agent-trust-hub — domain-context