skills/fikriaf/agentos/find-nearby/Gen Agent Trust Hub

find-nearby

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
  • Ingestion points: The skill retrieves place names, types, and metadata from the external OpenStreetMap Overpass and Nominatim APIs in scripts/find_nearby.py.
  • Boundary markers: Absent. The instructions in SKILL.md do not specify the use of delimiters or 'ignore embedded instructions' warnings when presenting the API results to the agent.
  • Capability inventory: The skill utilizes network requests to well-known domains to fetch map data but does not have capabilities for file system modification or command execution.
  • Sanitization: Strings retrieved from the external API are not validated or sanitized before being included in the agent's context.
  • Risk: An attacker could intentionally name a place in OpenStreetMap with malicious instructions designed to influence the agent's behavior when that location is returned in a search.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 07:46 PM
Security Audit — agent-trust-hub — find-nearby