paperclip-create-agent

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the curl utility to communicate with the Paperclip API. These commands are standard for the skill's purpose of managing agent configurations and hire requests.
  • [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection by reading configuration data and comments from the Paperclip API.
  • Ingestion points: SKILL.md (Workflow steps 2, 3, 4, 8) fetches data from $PAPERCLIP_API_URL endpoints.
  • Boundary markers: Absent in the skill body for data retrieved from the API.
  • Capability inventory: The skill is capable of network operations (curl) to interact with the vendor's platform.
  • Sanitization: The skill does not perform explicit sanitization of the text retrieved from the API endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 07:40 PM