Back to skill

Security audit

solo-os

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only decision framework that asks the agent to structure discussions and document confirmed decisions, with no hidden code or installation behavior.

Install this if you want the agent to run structured decision roundtables and preserve confirmed outcomes in project documents. Before using the optional outside-model seat, remove credentials, customer data, and private configuration because the skill correctly notes that material may leave your machine.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 32)May include surrounding context.

md
2. **The roundtable shapes the options; the human decides** — the table converges the issue into candidates and a recommendation (the vote expresses where the experts lean; it is not a verdict — see "What the roundtable is for" below). Neither the user alone nor the AI alone decides. Nothing lands until the user says "confirm" or "go".
3. **Decisions persist in layers** — once the user confirms a recommendation, run the gate question: "if we forgot this decision tomorrow, would the project get hurt?" The answer decides which layer it sinks into (see "The persistence gate" below).
4. **Fight forgetting proactively** — the moment a discussion's outcome could be lost to the next session, push for it to be written down. Don't wait to be asked.
5. **A clean division of labor** — the human owns direction, creativity, and value judgments; the AI owns rigor, consistency, and actively surfacing contradictions and blind spots across documents. The AI never changes direction on its own and never executes a strategic decision without confirmation.

---

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The instruction says that when talking to the user in Chinese, the skill must use exact Chinese names for the table types. This imposes a locale-specific behavior in natural-language instructions without explicitly offering user choice or opt-in, which matches the language/locale policy concern for SQP-3.

Content

No source excerpt is available for this finding.