feedback
Send feedback to the Nexu team. Use when the user says /feedback followed by their message.
72
87%
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
Security
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 skill requires inserting the user's feedback verbatim into a shell command (--content "<ESCAPED_FEEDBACK>") and explicitly forbids filtering, so any secrets present in the feedback (API keys, passwords) would be embedded and output by the agent.
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
The skill reads outsider-authored free text from the runtime session JSONL (user/assistant messages from other participants), assembles it into `conversationContext`, and sends it to an internal API in `submit-feedback.mjs`, making indirect prompt-injection possible even though it doesn’t directly paste into the current agent LLM prompt.
- Repository
- nexu-io/nexu
- Commit
dadfb1c
- 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.