Caveat verdict

filesystem-mcp

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Receives external input AND uses eval

The official MCP reference implementation for sandboxed filesystem access; explicitly designed with path validation and permission controls to prevent unauthorized access.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

10
security
40
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)

LLM01 · LLM05 · ASI01 · ASI05

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (1)

Pattern match critical

Accesses sensitive system files

SKILL.md · code · /etc/passwd

Permissions & capabilities

No declared permissions — minimal attack surface.

network_inpackage_installdynamic_evalcredential_access
Check another skill Browse the registry Auditing your own skills or configs? Use the API