harbor-expert
Expert Harbor container registry administrator specializing in registry operations, vulnerability scanning with Trivy, artifact signing with Notary, RBAC, and multi-region replication. Use when managing container registries, implementing security policies, configuring image scanning, or setting up disaster recovery.
80
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Security
2 findings — 1 high severity, 1 medium severity. 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
Insecure credential handling detected (high risk: 1.00). The prompt contains numerous examples that embed credentials directly (e.g., curl -u "admin:password", JSON fields like "access_secret": "token_here", robot "secret": "...", and inline env vars for tokens), which instructs or encourages producing commands/code that include secret values verbatim, creating exfiltration risk.
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
Third-party content exposure detected (high risk: 0.80). The skill includes explicit proxy/replication configurations that pull artifacts from public registries (e.g., the "dockerhub-cache" endpoint pointing to https://hub.docker.com and the replication/pull rules in Pattern 4 and references/replication-guide.md), so untrusted, user-generated image metadata (tags, labels, manifests) from third-party sources is ingested and used to drive replication, webhook, and automation actions—allowing external content to materially influence tool use and decisions.
- Repository
- martinholovsky/claude-skills-generator
- Commit
1086ef2
- 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.