Back to skill

Security audit

Postemi growth

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently supports social posting through Postemi and requires user approval before creating scheduled posts.

Scheduling sends content to Postemi for later publication on selected accounts. Review the text, destination accounts, timezone, and times before approving; choose draft mode for calendar review. Assess the separate main Postemi integration before connecting accounts.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (3)

The workflow instructs the agent to schedule posts through Postemi without warning about external data sharing or subsequent publication.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

This is an instruction to schedule user-derived content through an external service, not merely a listing of available tools. The file does not warn that the content will be sent to Postemi and may be published automatically, or require user approval before scheduling.

Content

No source excerpt is available for this finding.

Unbounded Output

Medium
Category
Output Handling
Confidence
80% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · reference/review.md (reported line 32)May include surrounding context.

md
## The weekly review (15 minutes)

1. **Fill the log** for last week's posts.
2. **Rank** by comments plus shares plus saves (or engagement rate when reach
   differs a lot). Look at the top three and the bottom three.
3. **Find the pattern.** What do the winners share: topic, angle, hook,

The review workflow instructs scheduling posts through Postemi, including reuse on a second network, without warning about external sharing and subsequent publication.

Medium
Category
Output Handling
Confidence
89% confidence
Finding

These steps instruct the agent to schedule content rather than merely describe available tools. Scheduling sends the content to Postemi for subsequent publication on connected networks, but the file provides no warning about that disclosure or the additional audience reached by cross-posting.

Content

No source excerpt is available for this finding.