ClawHub
Back to skill

Security audit

Community Launch Runner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed launch-submission planning helper with scoped web checks and permissioned memory logging, with no artifact-backed malicious behavior.

Before installing, confirm that you want an agent to draft community launch materials and consult current platform rules. Review any regional channel choices, approve only the memory saves or registry proposals you want persisted, and do not use the skill to automate posting or solicit votes.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

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 69)May include surrounding context.

md
## Save Results

After delivering, ask: "Save these results for future sessions?" On confirmation, save to `memory/launch/community-launch-runner/YYYY-MM-DD-<launch-slug>-submissions.md` — see [Skill Contract](../../../references/skill-contract.md) §Save Results Template. Submission facts (platform, timestamp, status, URL) go to `memory/events/launches.ndjson` via an authorized `operation: propose` request to `registry-events.py` for [launch-registry](../../../protocol/launch-registry/SKILL.md) to promote — never write the dossier directly. Do not write memory without asking.

## Reference Materials

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file includes a dedicated Chinese/regional channel section and says the skill produces a regional channel matrix including Chinese communities, but it does not require explicit user locale/market selection before surfacing those channels. That can cause the agent to recommend outreach in a jurisdiction, language, or platform ecosystem the user did not request, creating compliance, reputational, and targeting risks rather than a direct code-execution issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.