skills/keejkrej/coss/coss-particles/Gen Agent Trust Hub

coss-particles

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Comprehensive analysis of the instructions and metadata shows no signs of malicious intent. The skill primarily directs the agent to reference UI examples from the vendor's official site.
  • [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface as it instructs the agent to fetch and process data from external JSON manifests located at https://coss.com/ui/r/*.json.
  • Ingestion points: External JSON manifests referenced throughout SKILL.md.
  • Boundary markers: None mentioned; the instructions do not advise the agent to ignore instructions that may be embedded within the retrieved component code.
  • Capability inventory: Fetching, reading, and adapting external component code for user implementation.
  • Sanitization: No validation or sanitization of the external JSON content is defined in the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 10:08 PM
Security Audit — agent-trust-hub — coss-particles