ClawHub
Back to skill

Security audit

GitHub Actions

Security checks for vulnerabilities and agentic risk

Overview

This GitHub Actions skill is transparent and scoped to workflow design, debugging, hardening, and release guidance, with disclosed local notes and user-controlled GitHub access.

Install this if you want help with GitHub Actions workflows and are comfortable with local repo-context notes. Confirm before allowing workflow edits, live GitHub API actions, release changes, or deployment-affecting operations, and do not paste tokens or cloud keys into chat.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 41)May include surrounding context.

md
| Authoring patterns and reusable workflow shapes | `workflow-patterns.md` |

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md
- GitHub repository access if the user wants live run inspection or workflow changes
- Deployment credentials only through GitHub-managed secrets, environments, or OIDC

Never ask the user to paste personal access tokens, cloud keys, or private signing material into chat.

## CI/CD Examples

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 148)May include surrounding context.

md
- GitHub repository access if the user wants live run inspection or workflow changes
- Deployment credentials only through GitHub-managed secrets, environments, or OIDC

Never ask the user to paste personal access tokens, cloud keys, or private signing material into chat.

## CI/CD Examples

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 151)May include surrounding context.

md
- modify its own `SKILL.md`

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md
- GitHub repository access if the user wants live run inspection or workflow changes
- Deployment credentials only through GitHub-managed secrets, environments, or OIDC

Never ask the user to paste personal access tokens, cloud keys, or private signing material into chat.

## CI/CD Examples

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 166)May include surrounding context.

md
- structures safe release and deployment automation

This skill NEVER:
- assume write access to repositories or environments without confirmation
- suggest secret exfiltration, masking bypasses, or hidden credential handling
- normalize production deployment from untrusted pull request contexts

Static analysis

No suspicious patterns detected.