Back to skill

Security audit

sop-dev-001

Security checks for vulnerabilities and agentic risk

Overview

This is a Spanish-language sandbox workflow checklist with no executable code or hidden behavior.

Before installing, confirm you want a Spanish-language SOP that may activate for development tasks involving scripts, configuration, infrastructure changes, or deployments that need sandbox validation. It does not appear to install code, persist changes, use credentials, or run commands by itself.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description and operating instructions are entirely in Spanish, but the file does not state that Spanish is optional, user-selected, or required for a documented regional context. This can violate language/locale policy when users have not opted into that language.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger activates on receiving TASK_ASSIGNED for implementing scripts, configuration, infrastructure changes, or deployments requiring sandbox validation, which covers a very wide range of common development work. The file does not provide explicit inclusion/exclusion examples or narrower trigger constraints, so unintended invocation overlap is plausible.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description "Descripción de SOP: dev" is extremely broad and does not specify concrete trigger phrases, scope boundaries, or exclusion conditions. In a manifest file, this kind of generic description can contribute to ambiguous activation behavior because it does not clearly indicate what user requests should or should not match the skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The only user-facing description in the manifest is written in Spanish, and the file does not indicate that language selection is optional or that the skill is intentionally restricted to a Spanish-speaking context. This may violate language/locale policy guidance when a specific language is imposed without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.