ontopo

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration were detected. The skill interacts exclusively with the public Ontopo API to retrieve restaurant information.- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes data from an external source (Ontopo API) such as restaurant descriptions and menus.
  • Ingestion points: Data enters the agent's context through API responses handled in scripts/ontopo-cli.py.
  • Boundary markers: No specific delimiters or safety instructions are used to separate API-retrieved content from the agent's instructions.
  • Capability inventory: The skill is capable of network communication via httpx but does not possess dangerous capabilities like file writing or arbitrary command execution.
  • Sanitization: The script outputs raw text from the API without specific sanitization. This risk is assessed as low and is inherent to the skill's primary function of information retrieval.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 01:17 PM