Back to skill

Security audit

LYGO Champion: sancora unified minds

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed deprecated persona helper that points users to a successor skill, with a real but user-directed caution around its mutable npx install command.

Before installing, treat the displayed successor command as running mutable external code. Prefer verifying the ClawHub CLI version and the successor skill publisher/content first, and run the command only if you intended to replace this legacy SANCORA slug with `deepseekoracle/lygo-champion-council`.

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:8
Finding
Unpinned Remote Package Execution and External Skill Installation## Vulnerability Details **File Location**: `SKILL.md`, lines 8–9 **Vulnerability Type**: Unpinned third-party dependency and mutable remote installation **Risk Level**: Medium ### Vulnerable Code ```markdown > **Consolidated (Δ9 v2):** New installs → `lygo-champion-council`. This slug is legacy retention only. > `npx clawhub@latest install deepseekoracle/lygo-champion-council` ``` ### Technical Analysis The documented installation command instructs users to execute `clawhub@latest` through `npx`. The `latest` tag is mutable and does not identify a specific audited release or cryptographic digest. Depending on the local npm cache and configuration, `npx` can retrieve the referenced package from a remote registry and immediately execute its CLI with the invoking user's privileges. The command then installs the separately maintained `deepseekoracle/lygo-champion-council` skill, whose contents are outside this project's audited files. Neither the CLI nor the successor skill is pinned to an immutable version or integrity value. Consequently, the code and instructions ultimately executed can change after this package has been reviewed. ### Attack Path 1. An attacker compromises the npm package, its publisher account, the relevant registry resolution path, or the externally maintained successor skill. 2. The attacker publishes a malicious version selected by `clawhub@latest`, or replaces the successor skill's mutable content. 3. A user follows the installation command in `SKILL.md`. 4. `npx` downloads and executes the changed CLI without ensuring that it is the version previously audited. 5. The CLI or installed skill executes malicious code or introduces unsafe instructions in the user's environment. ### Impact Assessment Malicious code executed by the downloaded CLI could act with the operating-system permissions of the user running `npx`. Depending on those permissions and the behavior of the compromised dependency, t ...[truncated 517 chars]
Remediation
## Remediation Suggestions 1. Replace `clawhub@latest` with an exact, reviewed package version. 2. Enforce npm integrity verification through a lockfile, verified package digest, or equivalent immutable provenance mechanism. 3. Pin the successor skill to an immutable release identifier or content digest rather than a mutable name alone. 4. Document the expected publisher identity, package digest, and verification procedure. 5. Prefer downloading and inspecting the package before execution instead of immediately running newly fetched code through `npx`. 6. Execute installation with least privilege in a sandbox or otherwise restricted environment. 7. Re-audit both the pinned CLI release and successor skill whenever either pinned version is intentionally upgraded.
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding
The declared description says this skill is merely a deprecated slug directing users to another skill, implying little or no operational behavior. The supplied code instead implements a concrete self-check utility that reads local files, validates required resources, parses canon metadata, checks documentation content, and returns status codes. That is a materially different primary purpose from a passive deprecated alias. There are no declared triggers or permissions, but the code does access local repository files; while local file reads may be implementation details, the core mismatch is that the code is an active validator rather than a deprecation stub.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The declared description suggests this skill is merely a deprecated alias or legacy slug with no substantive behavior. However, the supplied code actively accesses a local JSON resource and outputs a specific SHA-256-related value. That is a materially different primary purpose and an undeclared capability, so the description does not accurately represent the code's behavior.

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding
Using `npx clawhub@latest` pulls and executes the newest package version at install time, which is a classic supply-chain risk. If the package or one of its dependencies is compromised, users following the instruction may run attacker-controlled code without review.

Static analysis

No suspicious patterns detected.