us-ccpa-expert

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface (Category 8) because it is designed to read and process untrusted external data to perform compliance assessments.
  • Ingestion points: The skill uses file-reading tools including Read, Glob, and Grep to ingest external project documentation and data for analysis.
  • Boundary markers: The instructions lack specific delimiters or guardrails directing the agent to ignore or isolate instructions that may be embedded within the processed data.
  • Capability inventory: The skill is configured with the Write tool, allowing the agent to generate and persist files based on the analysis of ingested content.
  • Sanitization: No sanitization, filtering, or validation processes are described for handling external inputs before they are interpreted.
  • [EXTERNAL_DOWNLOADS]: The skill references a JSON crosswalk file hosted on the author's GitHub Pages domain (grcengclub.github.io). This is a standard vendor-provided resource for regulatory framework mapping and represents normal operational functionality for a GRC-focused skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:27 PM
Security Audit — agent-trust-hub — us-ccpa-expert