Security audit

Centres Sociaux

Security checks for vulnerabilities and agentic risk

Overview

This is a French-language reference and drafting skill for managing social centers, with no executable code or hidden high-risk behavior found.

Reasonable to install if you want help drafting and structuring French social-center documents. Treat the regulatory figures, funding amounts, and process details as drafting support and verify them against current CAF/CNAF guidance before official submission.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: Le titre et la description présentent le skill exclusivement en français et le positionnent comme expert des centres sociaux en France, sans indiquer que la langue de réponse peut s'adapter à la préférence de l'utilisateur. Cette formulation peut constituer une contrainte implicite de langue/locale sans opt-in explicite.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.