fall

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill includes a clear medical safety disclaimer specifying that it is not intended for handling acute injuries or replacing professional medical assessments.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it captures user-provided descriptions of fall events and later retrieves this information to generate comprehensive risk reports. This pattern allows potentially untrusted data to re-enter the agent's context.
  • Ingestion points: User input parsed into fall record descriptions (SKILL.md, Step 3).
  • Boundary markers: Absent; the agent is not instructed to isolate or ignore instructions embedded within the stored description text.
  • Capability inventory: The skill is restricted to Read and Write tools (SKILL.md frontmatter).
  • Sanitization: No explicit content sanitization or validation logic is defined for the textual descriptions stored in data/fall-risk-assessment.json.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 05:26 AM
Security Audit — agent-trust-hub — fall