Skills
Navigate
skills/automattic/agentic-analytics/refresh-cache/Gen Agent Trust Hub

refresh-cache

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from S3, which is an attack surface for indirect prompt injection. Ingestion points: reads ~/.config/agentic-analytics/bucket.json and external S3 bucket data. Boundary markers: absent. Capability inventory: executes local Python scripts (refresh_cache.py, pull_parsely_dpl.py) and shell commands. Sanitization: absent.
  • [DATA_EXPOSURE]: The skill reads the local configuration file ~/.config/agentic-analytics/bucket.json to identify the AWS bucket and profile to use. This is standard configuration management for the skill's intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 02:02 PM
Security Audit — agent-trust-hub — refresh-cache