Skills
skills/gooseworks-ai/gooseworks-skills/contact-cache/Gen Agent Trust Hub

contact-cache

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it ingests data from external CSV files provided by the user.
  • Ingestion points: Data is read in scripts/cache.py from files specified in the --csv argument.
  • Boundary markers: The skill does not use specific markers or warnings to delimit untrusted data stored in the cache.
  • Capability inventory: Includes local file read/write and console output capabilities.
  • Sanitization: The skill uses standard CSV parsing without additional sanitization of the values within the CSV fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:06 PM
Security Audit — agent-trust-hub — contact-cache