Security audit

slack-e2e

Security checks for vulnerabilities and agentic risk

Overview

ClawScan’s verdict is benign with medium confidence: the reported memory-related alerts were judged expected for the skill’s purpose, though the scan was partial.

The verdict is benign, but benign does not mean risk-free. Consider the medium confidence and partial scan: some referenced paths were not available to inspect, so the evidence is incomplete.

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

Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
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 (2)

Memory Manipulation

High

Category: Memory Poisoning
Confidence: 80% confidence
Finding: Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
Content: Scanner excerpt · user-oauth.md (reported line 98)May include surrounding context.
md
Cleanup deletes only the returned message ID in the leased channel and checks that exact timestamp for absence. A rejected delete, failed readback, lost lease, or ambiguous create is not a pass. Do not bulk-delete history, blindly replay a write, or acquire a different credential to clean this run. Resolve current lease authority and exact ownership with the pool owner first.

Context Window Stuffing

Medium

Category: Memory Poisoning
Confidence: 80% confidence
Finding: Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
Content: Scanner excerpt · features.md (reported line 10)May include surrounding context.
md
## Native operations | Method | Recipe and evidence | | ------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `doctor()` | Same-lease identity/channel/Gateway readiness; capability matrix and advertised-scope diagnostics. It does not post a test message.