Back to skill

Security audit

Fidacy Artifact Anchoring

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent document-hashing purpose, but it asks users to run an unpinned third-party MCP package against potentially sensitive files.

Review this before installing. Use it only if you are comfortable running Fidacy's MCP package locally on the files you pass to it, and prefer a pinned, reviewed package version with limited filesystem access and a narrowly scoped, revocable API key.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:27
Finding

Unpinned Third-Party MCP Package Is Downloaded and Executed

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 27–29
Vulnerability Type: T08: Insecure Dependencies
Risk Level: Medium

Vulnerable Code Snippet

markdown
1. You need the Fidacy MCP server (`npx -y @fidacy/mcp`) with an engine API
   key (free at https://app.fidacy.com/signup, scope assess:write).

Technical Analysis

The Skill instructs users to run npx -y @fidacy/mcp without specifying an immutable package version or integrity hash. The -y option suppresses interactive confirmation, while the absence of a version causes package resolution to depend on the npm registry state at execution time.

The project does not include the MCP server implementation, a package lockfile, vendored source, or integrity metadata. Consequently, the code executed by this instruction may differ from the code originally reviewed. The documentation claims that files are hashed locally and that only SHA-256 digests are submitted, but this behavior cannot be verified from the supplied project.

This creates a supply-chain trust boundary: compromise of the package, its publisher account, its dependency graph, or the relevant registry response could result in arbitrary code running with the invoking process's permissions.

Attack Path

  1. An attacker compromises the @fidacy/mcp package, its publisher account, or a transitive dependency and publishes a malicious release.
  2. A user follows the Skill's instruction and executes npx -y @fidacy/mcp.
  3. npm resolves and downloads the unpinned package release.
  4. npx executes the downloaded package without requesting confirmation.
  5. The malicious package runs with the user's or Agent's local privileges.
  6. It may access the supplied Fidacy API key, artifact paths and readable files, misuse available credentials, transmit data, or execute additional commands.

Impact Assessment

Successful exploitation could provide code execution under the account running npx. The practical scope inclu ...[truncated 571 chars]

Remediation
View remediation

Remediation Suggestions

  1. Pin the MCP package to an exact, reviewed version rather than resolving the latest release:
    bash
    npx --yes @fidacy/mcp@<exact-reviewed-version>
    
  2. Verify the package's registry provenance and integrity before execution. Publish and validate expected package checksums or signatures.
  3. Include a lockfile or vendor the auditable MCP implementation and its dependency metadata with the Skill.
  4. Avoid suppressing confirmation with -y in security-sensitive setup instructions unless execution is otherwise verified and controlled.
  5. Run the MCP server in a sandbox with narrowly scoped filesystem access, restricted outbound networking, and no unnecessary environment variables or credentials.
  6. Provide the API key only to the MCP process, use the minimum required scope, and support short-lived or revocable credentials.
  7. Document and enforce the exact network destinations and request fields used during anchoring.
  8. Independently verify through tests or inspectable source that artifact contents remain local and only the intended SHA-256 digest and necessary metadata are transmitted.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill instructs users to run an MCP server via npx -y @fidacy/mcp without pinning an exact package version or integrity hash. This creates a supply-chain risk: future package updates, account compromise, or malicious dependency changes could cause users to execute unexpected code at install/runtime.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

md
- Call the `check_artifact` tool with the file path or digest.
   - Drop the file at https://fidacy.com/verify (hashed in the browser, never
     uploaded).
   - Query the public API: `GET https://api.fidacy.com/v1/verify/artifact?sha256=<hex>`.

A freshly anchored digest is on the tamper-evident chain immediately and shows
"pending Bitcoin confirmation" until the next checkpoint confirms (about one