skills/pixazo-ai/skills/boogu-image/Gen Agent Trust Hub

boogu-image

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEDATA_EXFILTRATIONREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [DATA_EXFILTRATION]: The skill instructs the agent to access ~/.pixazo/api-key and the PIXAZO_API_KEY environment variable. These credentials are transmitted to gateway.pixazo.ai to authenticate image generation requests. While this is standard for the service, it involves reading sensitive file paths and network transmission to a non-whitelisted domain.\n- [REMOTE_CODE_EXECUTION]: The skill provides instructions to execute npx skills add Pixazo-AI/skills, which downloads and runs code from a remote source. It also suggests fetching instructions from https://www.pixazo.ai/models/boogu-image.md.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided prompts and reference images which are then interpolated into API requests.\n
  • Ingestion points: User prompts and reference image data processed in SKILL.md.\n
  • Boundary markers: Absent; there are no instructions to delimit user input or ignore embedded commands.\n
  • Capability inventory: Network request capabilities via curl, requests, and fetch tools.\n
  • Sanitization: Absent; the skill does not define validation or filtering for user-provided inputs.\n- [EXTERNAL_DOWNLOADS]: The skill references external resources for configuration and related skill installation, targeting www.pixazo.ai and the Pixazo-AI/skills repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 09:02 PM