meeting-briefing-skill

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructions create a surface for indirect prompt injection by directing the agent to ingest data from untrusted external sources.
  • Ingestion points: As detailed in SKILL.md (Step 3), the agent is instructed to pull context from user emails and chat logs (Slack/Teams).
  • Boundary markers: The instructions do not define clear delimiters or provided warnings to the agent to disregard potential instructions embedded within the ingested messages.
  • Capability inventory: The skill allows the agent to synthesize summaries from a broad range of internal systems including CRM, CLM, and document repositories.
  • Sanitization: There is no evidence of sanitization or validation logic to filter out potentially malicious content from the ingested data.
  • [SAFE]: According to the SOURCE.md file, this skill is a mirrored version of a toolkit provided by a trusted organization's public repository. The functionality described is consistent with the stated purpose of a legal preparation assistant and does not demonstrate malicious intent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 09:08 AM
Security Audit — agent-trust-hub — meeting-briefing-skill