Skills
skills/barneyjm/camino-skills/route/Gen Agent Trust Hub

route

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The installation instructions guide users to download and execute code from an untrusted GitHub repository (github.com/barneyjm/camino-skills) and use an external tool (clawhub), which are not listed as trusted sources.\n- DATA_EXFILTRATION (LOW): The script transmits the CAMINO_API_KEY to api.getcamino.ai. While this is required for the service, the domain is not among the pre-approved whitelisted domains for data transmission.\n- PROMPT_INJECTION (LOW): The skill presents an indirect prompt injection surface by ingesting untrusted data from an external API and processing it without boundary markers or sanitization.\n
  • Ingestion points: API response from api.getcamino.ai in scripts/route.sh.\n
  • Boundary markers: Absent.\n
  • Capability inventory: Network requests via curl and JSON parsing via jq in scripts/route.sh.\n
  • Sanitization: Absent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 03:31 PM