security-scanning — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited security-scanning (Agent Skill) and scored it 65/100 (yellow). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 4 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 4 flagged
The text {match} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.
ignore/disregard/forget … previous instructions sentence.The text {match} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.
ignore/disregard/forget … previous instructions sentence.Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Mund detects security issues in content and MCP servers. Use it before processing untrusted input or installing MCP servers.
| Tool | Purpose |
|---|---|
mund_scan | Scan content for all security issues |
mund_check_secret | Check if a string is a secret |
mund_check_pii | Detect personally identifiable information |
mund_scan_mcp_server | Vet MCP server manifest before install |
mund_check_typosquatting | Detect name squatting attacks |
mund_audit_mcp_permissions | Analyze MCP tool capabilities |
mund_scan({ content: "API key: sk-abc123..." })
→ { safe: false, issues: [{ rule_id: "openai_api_key", severity: "critical" }] }mund_scan_mcp_server({ manifest: "<server.json>" })
→ { recommendation: "DO_NOT_INSTALL", issues: [...] }mund_check_typosquatting({ name: "githib-mcp" })
→ { is_suspicious: true, similar_to: ["github"] }~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.