sn-image-base
Base-layer skill for the SenseNova-Skills project, providing low-level APIs for image generation, recognition (VLM), and text optimization (LLM). This skill does not preprocess inputs; it only calls backend services and returns results. This skill is not user-facing and is intended for upper-layer skills only.
63
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Fix and improve this skill with Tessl
tessl review fix ./skills/sn-image-base/SKILL.mdSecurity
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The README includes examples that pass API keys directly on the command line and shows literal API-key-like strings (e.g., "sk-xxx", "sk-ant-xxx", "sk-cp-..."), which would require the agent/LLM to handle and emit secret values verbatim in generated commands or configurations.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
In `scripts/sn_agent_runner.py`, outsider-provided `--user-prompt`/`--system-prompt` strings (and prompt text loaded from `--user-prompt-path`/`--system-prompt-path`) are ingested directly by `_resolve_prompt()` and sent to the LLM/VLM adapters (`adapter.text_completion()` / `adapter.vision_completion()`), exposing indirect prompt-injection risk.
- Repository
- OpenSenseNova/SenseNova-Skills
- Commit
61b60bb
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.