baoyu-cover-image
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (e.g.,
bun,npx,baoyu-image-gen,codex-cli) to invoke image generation backends. It includes procedures for discovering these executables in standard configuration paths (~/.baoyu-skills/) or by searching the directory tree.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted user content (article titles, summaries, keywords) and interpolates them directly into image generation prompts. It relies on standard Markdown headers for structure in theprompts/cover.mdtemplate but lacks robust sanitization or specific instructions to ignore embedded commands within the input text.\n- [EXTERNAL_DOWNLOADS]: The skill utilizesnpxto execute wrappers, which can trigger automatic downloads of packages from public registries if the required tools are not cached locally on the system.
Audit Metadata