deps-analyzer
Verdict safe, but 2 findings (2 medium), mainly data exfiltration, social engineering. Most recent scan 2026-02-06.
The deps-analyzer skill presents MEDIUM security concerns primarily related to data exposure and social engineering through incomplete disclosure. The skill transmits project dependency information to OpenAI's API without clearly disclosing this in the description, which could surprise users who expect a local-only analysis tool. While the skill appears to serve a legitimate purpose (dependency analysis), the lack of transparency about external API usage and data transmission constitutes a security and privacy concern. The skill would benefit from explicit disclosure of its external dependencies, data handling practices, and user consent mechanisms. No critical threats like command injection or credential theft were detected, but the transparency issues should be addressed before widespread use.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
The two scanners disagree: Cisco found nothing and SkillSpector says do not install. One of them has a blind spot here; read the skill before trusting either. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Find unused and outdated dependencies. Use when your package.json is a mess.
- Package
- 7 files, 98 KB
- SKILL.md
- 287 words, 12+ sections
- Code
- TypeScript (2)
SKILL.md covers: Deps Analyzer · Quick Start · What It Does · Usage Examples · Audit current project · Auto-remove unused deps · Check a specific directory · Best Practices · When to Use This · Part of the LXGIC Dev Toolkit · Requirements · How It Works
Findings
MEDIUM Hardcoded External API Dependency Without User Consent Data Exfiltrationllm
The skill requires OPENAI_API_KEY environment variable and sends project dependency data to OpenAI's GPT-4o-mini API without explicit user consent or disclosure in the description. This constitutes potential data exposure as the skill transmits information about the user's project structure, dependencies, and potentially sensitive package names to a third-party service. The YAML description does not mention external API calls or data transmission.
SKILL.md
Requirements section states: 'Needs OPENAI_API_KEY environment variable' and 'How It Works' section reveals: 'Sends the results to GPT-4o-mini for analysis'. The description field only says 'Find unused and outdated dependencies' with no mention of external API usage.MEDIUM Misleading Description - Undisclosed External Dependencies Social Engineeringllm
The skill description 'Find unused and outdated dependencies. Use when your package.json is a mess' creates the impression of a local analysis tool, but the skill actually requires external API access (OpenAI) and transmits project data externally. This is social engineering through omission - users may not realize their dependency information is being sent to third-party services when they use this skill.
SKILL.md
YAML description: 'Find unused and outdated dependencies. Use when your package.json is a mess.' vs actual behavior documented in 'How It Works': 'Sends the results to GPT-4o-mini for analysis'. No mention of external API calls in the description.What is in the package
| File | Kind | Size |
|---|---|---|
README.md | doc | 693 B |
SKILL.md | doc | 1.9 KB |
package-lock.json | config | 89 KB |
package.json | config | 694 B |
tsconfig.json | config | 251 B |
src/cli.ts | script | 2.2 KB |
src/index.ts | script | 2.7 KB |
External hosts referenced
registry.npmjs.org github.com feross.org www.patreon.com lxgicstudios.com lxgicstudios.substack.com opencollective.com paypal.me tidelift.com x.com
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
OPENAI_API_KEY
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://clawhub.ai/skills/deps-checker
- Raw scan result: deps-checker-scan.json
- Badge for your README:
- Request a re-scan