Back to skill

Security audit

readiness-scoring

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because scanners report an unpinned command that installs a different skill and deployment settings that could remove unrelated shared-model columns and data.

Treat this as a review-level warning and do not assume the skill is safe to install. Before considering it, verify the external skill and pin its source to a reviewed version, and confirm deployment will preserve existing shared-model columns and data. Some analysis was partial, so the evidence does not cover every relevant expression or fully verify the installed skill.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (12)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The sole command performs skill installation, which is materially different from the described operational workflow. Although cargo-project is mentioned in the description and installation could be a prerequisite, the supplied code provides only that installation step. Any behavior of the downloaded skill is not available for verification.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

The score aggregation, hourly schedule, and threshold-based stages support the declared purpose. However, the exhaustive additionalColumns configuration introduces a material destructive effect beyond maintaining readiness fields: existing workspace columns not listed here are removed, including their values. The description does not disclose that behavior. Event decay and Slack notifications are not implemented in this chunk, but their absence from a partial code sample is not itself evidence of a mismatch.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The hourly schedule and decay calculation support the declared scoring purpose. However, deleting unrelated existing columns is a material, undeclared side effect beyond maintaining a readiness score. The supplied code explicitly documents this replacement behavior but does not preserve other columns. Account-level aggregation and Slack notifications are not present in this chunk; their absence alone does not establish a mismatch because they may be implemented elsewhere.

Content

No source excerpt is available for this finding.

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 130)May include surrounding context.

md
file. Then run `node --import tsx evals/contract.mjs` from this skill's folder, followed by

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 220)May include surrounding context.

md
- `node --import tsx evals/contract.mjs` passes against the adapted resources

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 194)May include surrounding context.

md
- **The play reads `readiness_stage`, and only that.** (`infra/plays/route-ready-accounts.ts`) A raw score

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 196)May include surrounding context.

md
- **`changeKinds: ["added"]` stays.** (`infra/plays/route-ready-accounts.ts`) Unify Accounts is

Deploying the readiness score can delete unrelated columns and their data from the shared Account Events model.

High
Category
Excessive Agency
Confidence
98% confidence
Finding

The declaration adopts a shared Account Events model but supplies an authoritative additionalColumns list containing only readiness_contribution. Under the stated deployment semantics, deploying it without manually merging existing columns deletes unrelated columns and stored values, potentially breaking other pipelines; the warning documents the hazard but does not enforce preservation.

Content

No source excerpt is available for this finding.

Deploying readiness scoring can delete unrelated account columns and their stored values.

High
Category
Excessive Agency
Confidence
98% confidence
Finding

The adopted Unify Accounts model declares only the two readiness columns in a list documented as replacing all existing additional columns. Deploying this template unchanged into a populated workspace can therefore delete unrelated account data and disrupt every consumer of those columns; comments alone do not prevent the destructive operation.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The installation command executes an unpinned npm CLI and retrieves an external skill without an immutable revision. Although this is not an MCP server, compromised or unexpectedly changed upstream content could execute code with the agent's local privileges or introduce instructions into a workflow that can modify shared production models.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 95)May include surrounding context.

npx skills add getcargohq/cargo-skills --skill cargo-project

text

Then read `.agents/skills/cargo-project/SKILL.md` directly; no session reload is needed. Complete its
bootstrap and use its authoring, state, plan, and deployment rules throughout. Stop before any
template work if the skill cannot be installed or read.