chat-summarization-va

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user input from chat transcripts (sys_cs_message) and context entries (sys_cs_context_entry) without explicit boundary markers or sanitization. This creates an indirect prompt injection surface where malicious instructions in a chat session could influence the generated summary written to work_notes.
  • Ingestion points: Data enters the agent context from the sys_cs_message and sys_cs_context_entry tables in SKILL.md.
  • Boundary markers: There are no delimiters or warnings to ignore embedded instructions in the summary template provided in Step 5.
  • Capability inventory: The skill uses SN-Update-Record, SN-Add-Work-Notes, and SN-Natural-Language-Search tools to read and write content.
  • Sanitization: No filtering or escaping of external content is performed before interpolation into the summary prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:24 PM
Security Audit — agent-trust-hub — chat-summarization-va