1 file · 15 lines · 1.1 KB
View on GitHub
Daniel Avila fix(components): clear every claude plugin validate error in the catalog #1071 dd830a9Oct 22, 2026
- langsmith-tracing.json 15 lines · 1.1 KB
langsmith-tracing.json
JSON
{
"description": "Automatically send Claude Code conversation traces to LangSmith for monitoring a..."
"hooks": {
"Stop": [1 item]
}
}
Scanned by NVIDIA SkillSpector
Automated static analysis (no LLM) · v2.12.0 · 2026-10-23
Partial analysis: some checks could not run on this component.
9 observations
scanner score 50/100
SkillSpector looks for patterns such as shell commands, credential access, network calls or unpinned dependencies. An observation is something worth reading in the files before you install, not a confirmed vulnerability. Components that run code locally, like hooks, MCP servers and security tooling, naturally show more of them.
- Autonomous Decision MakingExcessive Agency · SKILL.md:3
- Autonomous Decision MakingExcessive Agency · langsmith-tracing.json:2
- Without declared permissions the skill's intent is opaque and cannot be validated.MCP Least Privilege · SKILL.md:1
- MCP server references in the skill manifest without version pinning are a rug-pull risk.MCP Rug Pull · SKILL.md:1
- Sudo/Root ExecutionPrivilege Escalation · SKILL.md:3
Showing 5 of 9 observations. Learn more about NVIDIA SkillSpector or how components are reviewed.