skills/casemark/legal-plugin/search/Gen Agent Trust Hub

search

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill's primary function is to fetch and process data from untrusted external sources, creating a risk of indirect prompt injection.
  • Ingestion points: Commands such as casedev search webfetch, casedev search web, and casedev search legal ingest external content from the web and legal databases into the agent's context.
  • Boundary markers: The documentation lacks delimiters or explicit instructions for the agent to ignore any commands or instructions found within the fetched external data.
  • Capability inventory: The skill provides access to network resources (via webfetch) and internal documents (via vault search), which could be targeted by injected instructions.
  • Sanitization: No mechanisms for sanitizing or filtering the ingested external content are mentioned.
  • Command Execution (SAFE): The skill utilizes a custom CLI (casedev) for search operations. The documented command patterns are structured for data retrieval and do not contain shell injection, arbitrary command execution, or privilege escalation patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 05:42 AM