skills/casemark/skills/appeal-summary/Gen Agent Trust Hub

appeal-summary

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists entirely of Markdown-formatted instructions and lacks any executable scripts, binaries, or automated tasks.
  • [PROMPT_INJECTION]: The skill is designed to process untrusted external data (appellate documents, briefs, and transcripts), creating a surface for indirect prompt injection (Category 8). 1. Ingestion points: The 'Quick Start' section describes gathering external filings, briefs, and record materials for processing. 2. Boundary markers: Absent; the instructions do not define specific delimiters or instructions to ignore embedded commands within the source documents. 3. Capability inventory: None; the skill does not have access to any subprocesses, network operations, or file-system write capabilities. 4. Sanitization: Absent; no validation or filtering is performed on the content of the processed legal documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 07:56 PM