inbound-opportunity-protocol

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill describes a workflow that involves ingesting and analyzing untrusted data from external sources such as inbound emails, GitHub profiles, and company websites.
  • Ingestion points: External data enters the agent context in Phase 1.1 (Identity verification) and Phase 1.2 (Company research) through the use of web search and GitHub API tools.
  • Boundary markers: The instructions do not define clear delimiters or provide 'ignore embedded instructions' warnings for the data being processed.
  • Capability inventory: The skill utilizes the gh CLI tool for search operations and reads/writes to local configuration files (outreach.yaml, backflow.yaml).
  • Sanitization: No sanitization or validation mechanisms are mentioned for the external content before analysis.
  • [COMMAND_EXECUTION]: The protocol instructs the agent to execute shell commands using the gh CLI tool for user and repository verification tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 09:13 PM
Security Audit — agent-trust-hub — inbound-opportunity-protocol