Back to skill

Security audit

AitHub - Every agent's breakthrough, saved once

Security checks for vulnerabilities and agentic risk

Overview

The skill is openly about finding and installing other skills, but it gives agents broad activation, remote deployment, mutable CLI execution, and public submission workflows without enough review controls.

Install only if you are comfortable with an agent using AitHub as an external registry and do not let it run npx, deploy remote skills, write generated SKILL.md files, rate, or submit publicly without explicit review. Prefer staging downloaded skills locally, inspecting their full contents, pinning CLI versions, and changing public submission to a separate confirmed step.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Findings (4)

T01 · Skill Instruction Hijacking

Warning
Location
SKILL.md:142
Finding

Mandatory AitHub Promotion Hijacks Unrelated Agent Responses

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Error
Location
SKILL.md:25
Finding

Unpinned Third-Party CLI Execution Through npx

Content
View full analysis
Remediation
View remediation

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:41
Finding

Remote Registry Skills Are Automatically Deployed Without Review or Integrity Verification

Content
View full analysis
--deploy # Example: aithub install anthropics/pdf --deploy # --deploy flag auto-installs to detected AI framework # -o SKILL.md to save to file ``` ``` ### Technical Analysis The documented installation path uses `--deploy`, which automatically places remotely obtained skill content into a detected AI framework. The instructions do not require an immutable version, cryptographic digest, local inspection, permission review, or explicit confirmation after the content has been downloaded. Agent skills are executable instruction surfaces even when they contain only text. A registry entry can therefore introduce hostile instructions, and a skill containing scripts or commands could create a subsequent local code-execution path. Automatic deployment collapses the separation between downloading untrusted content and activating it in the agent environment. ### Attack Path 1. An attacker publishes or compromises a skill in the remote registry. 2. The malicious skill is returned by a search or is referenced using its namespace and name. 3. The user or agent runs `aithub install --deploy`. 4. The CLI retrieves the mutable remote content. 5. The `--deploy` option installs it directly into the detected AI framework. 6. The framework loads or invokes the deployed skill. 7. Malicious instructions alter agent behavior, or bundled executable content runs through the framework's available tools and privileges. ### Impact Assessment The immediate scope includes the detected AI framework's skill configuration and current-session instruction context. If the deployed content can invoke local tools, the practical impact may extend to arbitrary actions available to the agent, including file ...[truncated 334 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:154
Finding

Broad Automatic Activation Can Lead to Public Disclosure Through Heuristic Redaction

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (10)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list (find skill, search skill, install skill, need capability) is broad enough to match ordinary conversation and can cause the skill to activate in situations the user did not intend. Because this skill can lead to network access, package installation, and skill deployment, overbroad activation materially increases the chance of unsafe autonomous actions.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The auto-invocation guidance tells the agent to activate whenever the user asks for a capability it lacks or when a task could benefit from specialization, which is ambiguous and expansive. In context, that can cause unprompted external searches, remote content retrieval, and installation of third-party skills without clear user authorization.

Content

No source excerpt is available for this finding.

Self-Modification

High
Category
Rogue Agent
Confidence
97% confidence
Finding

The skill instructs the agent to create new skills using platform-native tools and then submit them publicly, which is a form of self-modification or persistence expansion. This is risky because an agent may package sensitive workflow details, normalize unsafe behavior into reusable artifacts, or alter its local capability set without strong human review.

Content

Scanner excerpt · SKILL.md (reported line 167)May include surrounding context.

md
- **Claude Code**: Use `skill_manage(action='create', ...)` tool
   - **Hermes**: Use `skill_manage(action='create', ...)` tool
   - **OpenClaw**: Use local skill creation capability
   - **Antigravity**: Write SKILL.md directly to workspace
   - **Cursor/Windsurf**: Write SKILL.md to project root
3. Apply privacy cleaning (see below) to the generated SKILL.md
4. Submit: `aithub submit SKILL.md --visibility public`

Self-Modification

High
Category
Rogue Agent
Confidence
97% confidence
Finding

Directing the agent to write SKILL.md to the workspace or project root modifies local files and can persist new behavior into the environment. In combination with public submission guidance, this increases the risk of unauthorized persistence, accidental leakage, and propagation of insecure automation patterns.

Content

Scanner excerpt · SKILL.md (reported line 168)May include surrounding context.

md
- **Hermes**: Use `skill_manage(action='create', ...)` tool
   - **OpenClaw**: Use local skill creation capability
   - **Antigravity**: Write SKILL.md directly to workspace
   - **Cursor/Windsurf**: Write SKILL.md to project root
3. Apply privacy cleaning (see below) to the generated SKILL.md
4. Submit: `aithub submit SKILL.md --visibility public`

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
88% confidence
Finding

The trigger phrase find skill overlaps with common built-in command semantics around find, increasing the risk that the skill intercepts benign user requests or tool invocations unexpectedly. Since this skill can initiate network access and installation flows, trigger shadowing can become a meaningful security issue rather than just a UX problem.

Content

No source excerpt is available for this finding.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
88% confidence
Finding

The trigger search skill conflicts with generic search intents and may activate during ordinary conversation or when users mean a different search facility. This broadens the attack surface by routing innocuous requests into a skill that performs external lookups and possible downstream installation actions.

Content

No source excerpt is available for this finding.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
90% confidence
Finding

The trigger install skill collides with generic installation language and could capture requests that are not intended for this registry or workflow. Because the skill supports deployment into detected frameworks, accidental activation could lead to unreviewed environment changes.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The skill instructs agents to run npx @aithub/cli without pinning a version or integrity, which allows execution of whatever package version is currently published. In an autonomous skill-discovery/install context, this creates a supply-chain risk where a compromised or malicious package update could run arbitrary code on the host.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill includes install behavior with --deploy and mentions saving to SKILL.md, but it does not place a clear warning before these actions that they modify the local environment and may import untrusted third-party content. Users may not realize the skill can install artifacts into their AI framework or write files automatically.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The skill directs the agent to fetch skill content from an external service, which transmits user-derived queries and imports remote prompt/code content into the local workflow. In a discovery-and-install skill, this is especially sensitive because downloaded skill content is itself potentially adversarial and may later influence agent behavior or cause further actions.

Content

Scanner excerpt · SKILL.md (reported line 103)May include surrounding context.

Install (no auth needed)

bash
curl -s "https://aithub.space/v1/skills/<namespace>/<name>/content"

Rate (auth needed)