ClawHub
Back to skill

Security audit

Skill Recommender Pro

Security checks for vulnerabilities and agentic risk

Overview

This skill recommends OpenClaw skills by checking installed skill names and public ClawHub metadata, with no artifact evidence of hidden persistence, credential access, destructive behavior, or automatic installs.

Installers should understand that the skill may inspect their installed skill list and query public ClawHub metadata to make recommendations. Treat its install commands as suggestions and review any recommended skills before installing them.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest describes an 'intelligent' recommender that analyzes installed skills with rule-based filtering and pattern matching, while the broader document claims semantic analysis, real-time ClawHub data, trending/popularity signals, and agent-assisted inference. However, the actual executable code shown only runs clawhub list, performs keyword matching, computes category gaps, and emits recommendations from a fixed COMPLEMENTARY_MAP, with no real API use, freshness/download retrieval, or semantic analysis implementation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases are broad, natural-language requests that can activate the skill during ordinary conversation, causing unintended execution of local CLI commands and recommendation logic. In an agent ecosystem, overbroad triggering increases the chance of surprise tool use, unnecessary environment probing, and user confusion about when analysis of installed skills occurs.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The notes state 'Only reads installed skill names and public metadata' and 'No access to config files, tokens, or sensitive data,' but the documented workflow later runs clawhub inspect skill-a and clawhub inspect skill-b to fetch per-skill details. That is broader than just reading installed skill names and creates a contradiction in the skill's own documentation about what data it accesses.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE.txt (reported line 12)May include surrounding context.

text
permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE
FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The error-handling section says 'ClawHub API error → Using cached recommendations...', but the included scripts contain no cache reads, cache writes, or fallback data source. This is an active contradiction between the documentation and the actual code shown in the skill file.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.