ClawHub
Back to skill

Security audit

Launch Feedback Synthesizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed launch-feedback analysis workflow with limited, purpose-aligned memory writes and no bundled executable code.

Before installing, confirm you are comfortable giving the skill launch feedback exports and allowing it to propose memory records about themes, claims, and launch outcomes. Avoid feeding confidential support data unless the workspace and memory store are appropriate for that data.

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 (1)

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 findings, ask: "Save these results for future sessions?" On confirmation, save to `memory/launch/launch-feedback-synthesizer/YYYY-MM-DD-<topic>.md` — see [Skill Contract](../../../references/skill-contract.md) §Save Results Template. Registry-bound facts (theme snapshot, outcome counts) go only to `memory/events/launches.ndjson` via an authorized `operation: propose` request to `registry-events.py`; [launch-registry](../../../protocol/launch-registry/SKILL.md) formalizes them. Do not write memory without asking.

## Reference Materials

Static analysis

No suspicious patterns detected.