Back to skill

Security audit

postey-ops

Security checks for vulnerabilities and agentic risk

Overview

The skill checks social post delivery and supports recovery with clear user control over restoring, retrying, and scheduling posts.

Review the separate Postey integration's account permissions before connecting it; its implementation is outside this bundle. Choose which deleted posts to restore and explicitly approve any retry or schedule that could publish content.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Behavior Manipulation

Medium
Category
Prompt Injection
Confidence
75% confidence
Finding

Subtle instructions detected that may alter agent decision-making or introduce hidden biases.

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

md
platform took the post. A post can sit in `PUBLISHING`, or reach `PUBLISHED` on one platform and
fail on another in the same post, because each platform publishes independently.

**Never tell the user something published because the call that scheduled it returned success.**
Read `postey://posts/{post_id}/publish-status` and say what it actually says.

## Checking a post

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 108)May include surrounding context.

text

If something failed, say what to do: reconnect the platform, restore the post if it was deleted, or
recreate and re-schedule. Do not retry a publish on the user's behalf without asking — a duplicate
post is worse than a late one, and the failure may have partially succeeded.

## Recovering a deleted post