skills/juxt/claude-plugins/elicit/Gen Agent Trust Hub

elicit

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest user-provided descriptions of business processes and requirements to generate Allium specifications.
  • Ingestion points: User input via conversation in the agent session.
  • Boundary markers: Not explicitly defined within the text flow, though the skill uses structured markdown blocks for the generated output.
  • Capability inventory: Use of allium check and allium analyse for static analysis of text files.
  • Sanitization: The skill guides the agent to translate user intent into a formal language rather than executing the user input directly.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the allium CLI toolset (specifically allium check and allium analyse) if available on the system. These tools are used for validating the syntax and consistency of the generated specification files and represent standard use of domain-specific tooling.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 07:24 PM