graphify
any input (code, docs, papers, images) - knowledge graph - clustered communities - HTML + JSON + audit report
41
42%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./plugins/sdlc/skills/graphify/SKILL.mdSecurity
2 findings: 1 critical severity, 1 high severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
The skill contains high-risk supply-chain and remote-execution/exfiltration patterns — a likely typosquatted package install ("graphifyy") plus instructions that enable running arbitrary agent subagents with Bash/Write privileges, starting an MCP server, and pushing graph data to remote Neo4j URIs (all of which can be abused to execute code or exfiltrate data).
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 explicitly tells the agent to "Ask the user for credentials" and to replace NEO4J_URI/NEO4J_USER/NEO4J_PASSWORD placeholders with actual values (embedding them in a push_to_neo4j call), which requires the LLM to receive and output secrets verbatim.
Low
Low-risk findings.
2 low severity findings. 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 Step 3B (Part B semantic extraction), the workflow dispatches LLM subagents (Agent tool, general-purpose) to read the contents of user-supplied documents/papers/images from the detected corpus (including via `/graphify <url>` / `add <url>` / GitHub clone), so outsider-authored free text inside those files is ingested directly by the LLM without selecting a specific item first.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill explicitly clones GitHub repositories at runtime (e.g. "https://github.com/<owner>/<repo>"), fetching remote repository content which is then fed into the Agent/subagent pipeline and thus injected into model context for extraction—this external content can directly control what the LLM sees and produces.
- Repository
- whimzyLive/nightshift-ai
- Commit
7741177
- 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.