mcp-engine-security-governance — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited mcp-engine-security-governance (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
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.
Security enforcement and governance through manage_security, manage_policy, and manage_audit. Keep curation separate from access control.
create_perspective, update_perspective) are curation — they change what users see, not what they can access.manage_model_connection { "operation": "get_current" } and state the intended scope before modifying anything security-sensitive.manage_security (create_role, set_role_filters, set_role_permissions) — read security-roles-guide first. For RLS, validate each affected role with run_query { "operation": "test_access", "query": "<small aggregate over the filtered data>", "spec": { "roles": ["<role>"] } } (both query and spec.roles are required). For OLS, exercise every changed table or column directly under the affected principals and verify each expected allow or denial; use targeted test_access queries or a manage_tests ols_validation matrix. An unrelated aggregate is not OLS evidence.manage_policy (status, evaluate, put, packs_apply with dry_run: true first) — policy-guide. Prefer deny rules over require_confirm for high-risk operations; require_confirm is best-effort UX, not a portable control.After security or governance work, report:
test_access or ols_validation results for each affected role, principal, and protected object.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.