ClawHub
Back to skill

Security audit

Launch Retro Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent launch-retrospective helper that discloses its reads and memory writes and requires user confirmation for saved results.

Before installing, be aware that the skill is intended to process launch analytics and save retrospective outputs into memory or registry event files. Only provide analytics exports you are comfortable using in this workflow, and review any proposed saved results before confirming persistence.

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 70)May include surrounding context.

md
## Save Results

On user confirmation, save to `memory/launch/launch-retro-analyzer/YYYY-MM-DD-<launch-or-product>-retro.md` — see [Skill Contract](../../../references/skill-contract.md) §Save Results Template. Ask "Save these results for future sessions?" first; do not write memory without asking. Registry-bound facts (the outcome snapshot) go only to `memory/events/launches.ndjson` via an authorized `operation: propose` request to `registry-events.py` — never to the registry records themselves.

## Reference Materials