symptom-checker-triage
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a rule-based triage logic entirely within a local Python script, utilizing predefined dictionaries for symptom matching.
- [SAFE]: Execution is restricted to standard library components (
re,argparse,json). No third-party packages with high supply-chain risk are utilized. - [SAFE]: The skill lacks dangerous capabilities such as network access, file system modification, or subprocess spawning.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided symptom descriptions which could theoretically contain malicious instructions.
- Ingestion points: Symptom strings passed via CLI arguments to
scripts/main.py. - Boundary markers: None identified for the LLM-to-script transition.
- Capability inventory: The script only performs string matching and prints structured text or JSON to the terminal; it has no side-effect capabilities to exploit.
- Sanitization: Uses regex matching and standard string normalization to identify symptoms.
Audit Metadata