Camp Planning Knowledge

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill architecture is susceptible to indirect prompt injection (Category 8) due to its data ingestion design.
  • Ingestion points: As documented in references/school-calendars/README.md, the skill utilizes a '3-Tier School Calendar Lookup' pattern that retrieves content from user-provided PDFs and external school board websites discovered via web searches.
  • Boundary markers: The provided reference files and instructions do not define delimiters or specific 'ignore embedded instructions' warnings for the agent when processing this external extracted content.
  • Capability inventory: The skill environment references execution of external scripts such as summer_dates.py (references/private-school-test-cases.md) and allows for automated web searching and local file writing within the pdfs/ directory.
  • Sanitization: There is no evidence of validation or sanitization protocols for content extracted from external sources before it is incorporated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 11:31 AM
Security Audit — agent-trust-hub — Camp Planning Knowledge