token-report

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill reads data from an internal Knowledge Base and writes reports to local story directories. No external data transmission or network activity was detected.- [PROMPT_INJECTION]: The skill processes usage data from the Knowledge Base, which creates a surface for indirect prompt injection. However, given the local context and limited tool access, this does not pose a significant threat.
  • Ingestion points: Data returned from Knowledge Base queries.
  • Boundary markers: No explicit delimiters are used for the processed log data.
  • Capability inventory: Knowledge Base search and local file system write access.
  • Sanitization: The skill does not perform sanitization on the retrieved log entries before formatting them into a markdown report.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 09:46 PM