event-brief-planner

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the processing of external website content.
  • Ingestion points: SKILL.md (Step 2: URL check). The skill explicitly instructs the agent to read the page provided by the user and extract everything available.
  • Boundary markers: Absent; the skill lacks instructions to delimit or ignore instructions that might be embedded in the fetched web content.
  • Capability inventory: SKILL.md (calls get_marketing_context, search_content, get_voice_profile, and saves data via the briefs-integration.md protocol).
  • Sanitization: Absent; the skill does not specify validation or filtering for extracted content before it is used to generate marketing briefs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 01:21 PM