database
Verdict safe, but 1 finding (1 medium), mainly social engineering. Most recent scan 2026-02-05.
This skill is a NON-FUNCTIONAL SHELL with deceptive metadata. It promises comprehensive database management capabilities across multiple database systems (PostgreSQL, MySQL, SQLite, MongoDB, Redis) but contains ZERO implementation code. The primary security concern is MISLEADING DESCRIPTION (AITech-2.1) - users may trust this skill to handle sensitive database operations, but it cannot deliver any functionality. Secondary concerns include missing security metadata (no allowed-tools declaration), absent provenance information (no license/compatibility), and unenforceable safety rules. The 'always: true' flag is inappropriate for a database tool. While there's no active malicious code (no data exfiltration, no command injection), the deceptive nature and lack of implementation make this skill unsuitable for use. If this is a template or work-in-progress, it should not be distributed. If implemented in the future, it would require careful security review for SQL injection prevention, credential management, and proper input validation.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Database management and queries. Connect to SQL and NoSQL databases, run queries, and manage schemas.
- Package
- 1 file, 714 B
- SKILL.md
- 77 words, 5 sections
- Code
- None. Instructions only.
- Requires
- bins:
curljq
SKILL.md covers: Database 🗄️ · Supported Databases · Features · Usage Examples · Safety Rules
Findings
MEDIUM Misleading Description - No Implementation Provided Social Engineeringllm
The skill claims to provide 'Database management and queries' with support for PostgreSQL, MySQL, SQLite, MongoDB, and Redis, but contains NO implementation code (no Python or Bash scripts). The description promises features like 'Run SQL queries', 'Schema management', 'Data export/import', 'Backup and restore', and 'Performance monitoring', but there is no code to deliver these capabilities. This is deceptive metadata that misleads users about the skill's actual functionality.
SKILL.md:1
Description claims: 'Connect to SQL and NoSQL databases, run queries, and manage schemas' but script files show: 'No script files found.' The skill is an empty shell with no executable code.What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 714 B |
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/database
- Raw scan result: database-scan.json
- Badge for your README:
- Request a re-scan