Skills
Navigate
skills/yusukebe/skills/hono-review/Gen Agent Trust Hub

hono-review

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content from GitHub Pull Requests. \n
  • Ingestion points: PR diffs, descriptions, and commit logs are retrieved using gh pr diff and gh pr view in SKILL.md. \n
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious embedded instructions within the PR data. \n
  • Capability inventory: The agent has shell access via gh, git, and bun in SKILL.md. \n
  • Sanitization: The skill does not sanitize or validate the external PR content before processing it for review.\n- [REMOTE_CODE_EXECUTION]: The skill enables the execution of code downloaded from external, untrusted sources. \n
  • Evidence: The instructions in SKILL.md guide the agent to perform gh pr checkout and subsequently run bun run test on the contributor's code. \n
  • Context: While this is a standard maintainer workflow and requires explicit user confirmation, running tests on untrusted PR branches can lead to the execution of malicious code contained within the tests or lifecycle hooks.\n- [COMMAND_EXECUTION]: The skill relies on shell commands for its core functionality. \n
  • Evidence: Extensive use of gh, git, and bun commands to manage and evaluate the local and remote codebase.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 09:45 AM