skills/team-attention/hoyeon/verify/Gen Agent Trust Hub

verify

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to run repository-defined scripts.
  • Evidence: The workflow (Steps 3 and 4) instructs the agent to run commands like pnpm test, pnpm build, and other verification scripts found in the project's package.json or verification profiles.
  • Context: This is the primary purpose of the skill, and execution is limited to the local development environment.
  • [PROMPT_INJECTION]: The skill processes untrusted content from the repository, creating a surface for indirect prompt injection.
  • Ingestion points: The agent reads package.json, .hoyeon/verify/profile.json, and .hoyeon/verify/checklist.md to define and guide verification tasks (SKILL.md).
  • Boundary markers: The instructions do not define explicit delimiters or 'ignore embedded instructions' warnings for the agent to use when processing these files.
  • Capability inventory: The skill has the capability to execute shell commands, write files to the repository (.hoyeon/verify/*), and perform browser operations via chromux (SKILL.md).
  • Sanitization: No explicit sanitization or validation of the ingested file contents is described in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 02:16 AM
Security Audit — agent-trust-hub — verify