Back to skill

Security audit

context-diet

Security checks for vulnerabilities and agentic risk

Overview

ClawScan classifies this context-diet skill as benign: scanners found no AIG issues and two low or medium concerns judged purpose-aligned, though Skillspector coverage is partial.

The verdict is benign, but that does not mean risk-free. Consider whether broad activation cues suit your workflow, and keep in mind that Skillspector marked its analysis partial because three local references could not be resolved.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
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 104)May include surrounding context.

md
## Rules

- **Never delete without asking** — every trim item is a suggestion with evidence, the user decides
- **Token estimates are approximate** — state "≈" and the estimation method; don't pretend precision you don't have
- **Skills zone is the headline** — most users don't realize each installed skill's description sits in every turn; make this the "aha" moment
- **Last-used detection is heuristic** — check memory files for mentions, check if the skill's name appears in any conversation history; "never mentioned ≠ never used" but it's a strong signal

Activation conditions include broad session and performance cues without requiring a context-bloat audit request.

Low
Category
Trigger Abuse
Confidence
91% confidence
Finding

The skill says to run when the agent feels slower, before a long session, or periodically. These conditions can occur during unrelated tasks, and neither this section nor the frontmatter clarifies whether an explicit request is required, allowing unintended invocations.

Content

No source excerpt is available for this finding.