BulkPublish: Schedule Post

• Outcome: Pass
• Latest audit: Oct 13, 2026 · 2:22 PM UTC
• Version: 1.0.0

Overview

This is a documentation-only social posting helper for BulkPublish; it can guide public posting and RSS auto-publishing, but the behavior is disclosed and fits the stated purpose.

Install only if you intend the agent to help operate BulkPublish-connected social accounts. Review any action that publishes immediately, schedules posts, retries uncertain posts, or sets RSS feeds to publish mode, because those choices can create public content or ongoing automatic posting.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Tool Misuse: Tool Parameter Abuse, Chaining Abuse, Unsafe Defaults
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

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 · SKILL.md (reported line 194)May include surrounding context.

md

| `GET /api/rss-feeds` | List feeds (ordered by name) |
| `POST /api/rss-feeds` | Create — body `{name, feedUrl, channelIds, mode?, fieldMapping?}` |
| `PUT /api/rss-feeds/{id}` | Partial update — body `{name?, feedUrl?, channelIds?, mode?, fieldMapping?, enabled?}` |
| `DELETE /api/rss-feeds/{id}` | Delete |

- `mode` is `"draft"` or `"publish"`, **default `"draft"`** — draft: new feed items land as draft posts for review; publish: they are auto-published. `"publish"` needs a plan with RSS auto-publish (not Free): otherwise **403** `FEATURE_DISABLED`
- `feedUrl` must be a public http(s) RSS 2.0/Atom URL — the server validates it is reachable at create time

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

The skill description 'Use when the user wants to post to social media' is broad enough that an agent may invoke this skill for loosely related requests without confirming the user's intent to publish, schedule, or modify external-facing content. Because this skill can cause real actions on connected social accounts, over-broad routing increases the chance of unintended posting or scheduling rather than being a purely informational mismatch.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

The RSS Autopost section documents a mode that automatically publishes feed items to external accounts, but it does not foreground the operational risk that enabling 'publish' creates ongoing unattended posting. In a skill that can affect public social channels, insufficient warning can lead users or agents to configure persistent auto-posting without appreciating that future feed items will be posted automatically.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.