Security audit

Skill Foundry

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly aligned with its stated purpose, but it depends on missing execution and publishing files while describing credential-backed publishing to external services.

Review this package before installing or using it. Do not run the referenced Python command unless you have verified the actual script it will execute, and do not enable ClawHub or GitHub publishing until the target account, repository, token scope, and generated publish manifest have been checked manually.

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

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 (5)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 81)May include surrounding context.
md
- `SKILL.md`: English skill instructions.

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 94)May include surrounding context.
md
- `SKILL.md`: English skill instructions.

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 95)May include surrounding context.
md
- `SKILL.md`: English skill instructions.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The skill supports publishing generated artifacts to ClawHub and GitHub, which can modify external services and repositories, but the instructions do not prominently warn users about that side effect at the point of use. In a skill that automates generation and optional publication, insufficient disclosure increases the risk of unintended pushes, accidental exposure of generated content, or writes to the wrong remote target.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The file states that each generated skill folder includes bilingual documentation and later requires English and Chinese versions of both SKILL.md and README.md. This imposes a specific language/locale requirement as a default policy without indicating user opt-in or a documented regional/compliance justification.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.