addon-clause-extraction-citations

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a workflow for processing external document chunks, which introduces an indirect prompt injection surface.
  • Ingestion points: document_chunks (SKILL.md)
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore instructions' headers for the input text chunks.
  • Capability inventory: LLM-assisted clause extraction and JSON formatting (SKILL.md).
  • Sanitization: Employs strict JSON schema validation and mandatory verbatim source_quote anchoring to minimize the risk of fabricated or injected content.
  • [NO_CODE]: No scripts, executables, or configuration files are present in the skill package. The skill relies entirely on natural language instructions for the agent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 06:55 PM