Back to skill

Security audit

Postmately SMM Autopilot

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it flags an unpinned installer and a workflow that may send user content to an external service without a privacy warning; the scanners did not establish malicious intent.

Before installing, consider whether you trust Postmately to process the content you provide, and check what information could be sent to it. The scanner results also flag an installer that is not pinned to a reviewed version. The scan covered all three listed components, but its findings do not establish that the service is safe or that the integration handles every kind of content appropriately.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The installation command executes an unpinned npm package and selects skill content without an immutable revision. This introduces a supply-chain integrity risk if a subsequent release or repository change is compromised; the issue is the installer and skill source, not an explicitly versioned MCP server.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · README.md (reported line 34)May include surrounding context.

md
1. Create an API key in Postmately under Settings, then API.
2. Keep it in the environment as `POSTMATELY_API_KEY`.
3. Connect MCP: `https://api.postmately.com/mcp` with `Authorization: Bearer $POSTMATELY_API_KEY`.

In Claude Code:

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.

md
1. Create an API key in Postmately under Settings, then API.
2. Keep it in the environment as `POSTMATELY_API_KEY`. Never print it or
   commit it.
3. Connect MCP: `https://api.postmately.com/mcp` with
   `Authorization: Bearer $POSTMATELY_API_KEY`.

## Workflow

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md
If the user already has final images or clips, use `import_media` and
skip generation. Do not spend credits when the files already exist.

For a video edited on this machine, `list_clips` (or `GET https://api.postmately.com/v1/clips`,
no key) is Postmately's free hook gallery: people reacting, 1080x1920, with
meta to pick by (fits, mood, setting, a phone in hand, sample lines). The two
formats that travel furthest on TikTok are a hook and an app demo

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · README.md (reported line 39)May include surrounding context.

In Claude Code:

bash
claude mcp add --transport http postmately https://api.postmately.com/mcp \
  --header "Authorization: Bearer $POSTMATELY_API_KEY"

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 55)May include surrounding context.

md
## Links

- Postmately: https://postmately.com/
- Skill file: https://postmately.com/skills/smm-autopilot/SKILL.md
- MCP endpoint: https://api.postmately.com/mcp
- Skills for AI agents: https://postmately.com/en/skills/

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · README.md (reported line 56)May include surrounding context.

md
- Postmately: https://postmately.com/
- Skill file: https://postmately.com/skills/smm-autopilot/SKILL.md
- MCP endpoint: https://api.postmately.com/mcp
- Skills for AI agents: https://postmately.com/en/skills/

## License

The asset-generation workflow sends user content to Postmately without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow directs generation from user content and import of existing media without checking whether those materials are approved for third-party processing. Postmately integration is disclosed, which reduces concern, but local assets or unpublished business information could still leave the user's environment before the separate publishing-approval step.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

md
meta to pick by (fits, mood, setting, a phone in hand, sample lines). The two
formats that travel furthest on TikTok are a hook and an app demo
(`fits=hook-demo`, then the product's screens) and a hook and a wall of text
(`fits=wall`). Recipes: https://postmately.com/skills/postmately-video/SKILL.md

### 4. Validate before writing