acp-intent-traces

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches technical documentation and implementation guidelines from official developer portals and public repositories.
  • [DATA_EXFILTRATION]: Defines a standard commerce interaction for sending abandonment signals to a checkout session endpoint. This behavior is consistent with the skill's primary purpose and does not access sensitive system data.
  • [PROMPT_INJECTION]: The skill interacts with external web documentation which constitutes a surface for indirect prompt injection. Ingestion points: WebSearch and WebFetch for protocol specs. Boundary markers: None present. Capability inventory: Includes shell command execution and file system access. Sanitization: Not performed on the fetched specification data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 06:09 AM