inbound-opportunity-protocol

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze untrusted data from external sources, creating a surface for indirect prompt injection.
  • Ingestion points: Research involves fetching data from public websites, documentation pages, product pages, and GitHub profiles (using gh api).
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the external content being analyzed.
  • Capability inventory: The agent has the ability to execute CLI commands (gh), write research artifacts to the filesystem (contrib_engine/artifacts/), and modify local tracking files (outreach.yaml, campaign.yaml, tracked_conversations.yaml, backflow.yaml).
  • Sanitization: There are no explicit instructions for sanitizing or escaping content retrieved from external sources before it is processed or used to generate response drafts.
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) for identity verification and repository research. While these are legitimate tools for the stated purpose, they represent a capability that interacts with external services based on data gathered during research.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 04:22 PM