Back to skill

Security audit

Skillguard

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to run a local security-audit API for user-supplied SKILL.md text, with no evidence of hidden exfiltration, persistence, or destructive behavior.

Install only in an environment where you are comfortable running a local Python web service. Review or pin the Python dependencies if reproducibility matters, and verify the referenced scanner modules are present and from a trusted source before relying on the audit verdicts.

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:4
Finding

Unpinned Third-Party Dependencies

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, line 4
Vulnerability Type: Supply-chain risk from unpinned dependencies
Risk Level: Medium

Vulnerable Code

yaml
metadata: {"openclaw":{"emoji":"🏰","requires":{"bins":["python"]},"install":[{"id":"pip","kind":"uv","packages":["fastapi","uvicorn","pydantic","pyyaml"]}]}}

Technical Analysis

The installation metadata requests fastapi, uvicorn, pydantic, and pyyaml without exact versions or integrity hashes. Consequently, separate installations can resolve to different package releases and transitive dependency trees.

This does not demonstrate that any listed package is malicious. However, it creates a supply-chain weakness: a compromised future release, compromised transitive dependency, or unexpected incompatible release could be installed without a review of the newly resolved code. Integrity hashes are also absent, so the installer has no project-defined cryptographic allowlist for approved artifacts.

Attack Path

  1. An attacker compromises a listed package or one of its transitive dependencies and publishes a malicious release.
  2. A user installs the Skill after that release becomes eligible under unconstrained dependency resolution.
  3. The installer selects and downloads the affected release because no exact version or artifact hash is specified.
  4. Malicious package installation logic or imported runtime code executes in the installation or server process context.

This path requires an upstream package or distribution-channel compromise; the audited project itself does not retrieve or execute an explicit malicious payload.

Impact Assessment

Exploited dependency code would inherit the privileges of the user installing or running SkillGuard. Depending on those privileges and the malicious dependency behavior, the affected scope could include application data, files accessible to that account, environment variables, network ...[truncated 130 chars]

Remediation
View remediation

Remediation Suggestions

  1. Pin every direct dependency to an exact, reviewed version.
  2. Generate and commit a lock file that fixes the complete transitive dependency graph.
  3. Require cryptographic hashes for downloaded distributions where the installation system supports hash verification.
  4. Prefer an authenticated package index and prohibit unreviewed alternate indexes or dependency sources.
  5. Automate dependency vulnerability and provenance checks while requiring review before lock-file updates.
  6. Test upgrades in an isolated environment and deploy only approved artifacts.
  7. Include or explicitly declare the imported products.skillscan, products.scopecheck, and products.promptguard components so their provenance, versions, and implementations can be reviewed. Those modules were absent from the supplied artifact, so their internal security behavior was outside the available audit scope.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 20)May include surrounding context.

Audit a skill

bash
curl -s -X POST http://localhost:8005/v1/audit-skill \
  -H "Content-Type: application/json" \
  -d "{\"skill_content\": $(cat path/to/SKILL.md | jq -Rs)}" | jq