meetup-manager

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The documentation provides an installation command using the npx package runner to add the skill from the platform's registry.
  • Evidence: npx skills add kugchennai/MeetupManager@meetup-manager -g -y found in SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to ingest and act upon data from a remote REST API.
  • Ingestion points: Data enters the agent context through various API endpoints including GET /api/events, GET /api/speakers, GET /api/volunteers, and GET /api/checklists as documented in SKILL.md.
  • Capability inventory: The skill allows the agent to perform write operations, send emails via POST /api/email/test and POST /api/events/{eventId}/venues/{linkId}/request-email, and modify configurations such as PATCH /api/discord/config.
  • Boundary markers: There are no instructions for using delimiters or boundary markers to separate data from instructions when processing API responses.
  • Sanitization: No explicit data sanitization or validation logic is defined for the content retrieved from the external API.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 10:22 AM
Security Audit — agent-trust-hub — meetup-manager