oral-health-analyzer

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external health data provided by the user.
  • Ingestion points: The skill ingests data from user oral health records, medication logs, and nutrition data as described in scenarios 1, 2, 4, and 5 in SKILL.md.
  • Boundary markers: The instructions do not define any delimiters or warnings to ignore instructions that might be embedded within these ingested health records.
  • Capability inventory: Static analysis identifies no capabilities for command execution, shell access, network operations, or file system modifications within this skill.
  • Sanitization: There are no specified processes for validating, filtering, or sanitizing the external data before it is interpolated into the agent context.
  • [NO_CODE]: This skill consists solely of markdown instructions and metadata, with no associated scripts, binaries, or referenced executable files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:20 AM
Security Audit — agent-trust-hub — oral-health-analyzer