ClawHub
Back to skill

Security audit

Publer API

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Publer API reference skill for managing social posts, media, and analytics, with expected but sensitive posting and deletion abilities.

Install only if you intend to let an agent use your Publer API key. Use the minimum API scopes needed, keep the key private, and require the agent to preview and confirm exact accounts, content, schedule times, and post IDs before publishing, updating, or deleting posts.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
92% confidence
Finding

The documented delete flow accepts post_ids from a query parameter and presents deletion as a simple follow-up action, which creates a tool-parameter abuse risk if untrusted, ambiguous, or overly broad IDs are passed through. In this skill context, deletion affects real social-media assets, so improper parameter validation or confirmation could enable unauthorized or accidental bulk deletion.

Content

Scanner excerpt · SKILL.md (reported line 131)May include surrounding context.

md
### List and review scheduled posts
1. `GET /posts?state=scheduled`
2. Display as readable list: date, network, text preview
3. Offer to edit (`PUT /posts/{id}`) or delete (`DELETE /posts?post_ids[]=...`) on request

### Fetch analytics
1. For account-level charts: `GET /analytics/charts` to get available IDs, then `GET /analytics/:account_id/chart_data?chart_ids[]=...&from=...&to=...`

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · api-reference.md (reported line 382)May include surrounding context.

md
---

### Delete Posts
`DELETE /posts`

**Query Parameters:** `post_ids[]` — array of post IDs (required)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger text is broad enough to activate on general social-media automation requests, even when the user did not explicitly intend to use Publer. In a capability that can publish, update, and delete social posts, overbroad invocation increases the chance of acting in the wrong system or taking unintended actions with user-connected accounts.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill documents deletion capability without requiring an explicit user confirmation or warning before destructive operations. Because this API can remove scheduled posts across connected social accounts, a mistaken or ambiguous request could lead to irreversible content loss or workflow disruption.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.