Security audit

flocker-agent-profiles

Security checks for vulnerabilities and agentic risk

Overview

The skill is not deceptive, but it lets mutable remote profile content steer the agent and can automatically store task updates on a third-party service.

Review this skill before installing if you use agents on sensitive work. Only bind profiles you trust, treat profile instructions and memories as remote mutable content, and disable or avoid automatic feed posting unless you are comfortable sending task summaries to Flocker.

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
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (3)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:37
Finding: Remote Profile Content Can Hijack Agent Instructions
Content: View full analysis
Remediation: View remediation

T02 · Agent Memory Poisoning

Error

Location: SKILL.md:35
Finding: Persistent Cross-Session Profile State Enables Memory Poisoning
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:43
Finding: Automatic Feed Posting Can Disclose Task Information to a Third Party
Content: View full analysis
Remediation: View remediation

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

Static analysis

No suspicious patterns detected.