ClawHub
Back to skill

Security audit

socialcannon

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent SocialCannon API skill for managing real social media accounts, with sensitive actions disclosed and guarded by human-approval guidance.

Use this only for accounts you are comfortable letting an agent help manage. Keep the client secret in an environment variable or keychain, review any live publish, reply, delete, disconnect, retry, or post-mode repurpose action before approval, and prefer draft, scheduled, or preview workflows where possible. If enabling the optional MCP package, remember it will run with your SocialCannon credentials.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 153)May include surrounding context.

md
- Success: `{ "success": true, "data": { ... } }`
- Error: `{ "success": false, "error": "message", "code": "ERROR_CODE" }`

When extracting data from any response, always read from `response.data`, not from the response root. For example, the access token is at `response.data.access_token` — not `response.access_token`.

## Accounts

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 71)May include surrounding context.

bash
# Get a token
TOKEN=$(curl -s -X POST https://socialcannon.app/api/v1/auth/token \
  -H "Content-Type: application/json" \
  -d "{\"grant_type\": \"client_credentials\", \"client_id\": \"$SOCIALCANNON_CLIENT_ID\", \"client_secret\": \"$SOCIALCANNON_CLIENT_SECRET\"}" \
  | jq -r '.data.access_token')

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 81)May include surrounding context.

md
-H "Authorization: Bearer $TOKEN" | jq '.data'

# Publish a post (replace <account_id> with an ID from the list above)
curl -X POST https://socialcannon.app/api/v1/posts \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"accountId": "<account_id>", "content": "Hello from SocialCannon!"}'

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 107)May include surrounding context.

SOCIALCANNON_CLIENT_SECRET: "${SOCIALCANNON_CLIENT_SECRET}"

text

**Claude Desktop** — add an entry under `mcpServers` in `claude_desktop_config.json` with the same pinned `command`/`args`. If your MCP client can only take the secret as a literal value in its config file, make that file readable only by you (`chmod 600`), never commit or sync it, and click **Generate API Secret** under **Settings → API Keys** to replace the secret if the file is ever exposed.

The REST API documented below remains fully available; MCP is an optional convenience layer over the same endpoints.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 330)May include surrounding context.

Step 1 — Initialize upload

bash
curl -X POST https://socialcannon.app/api/v1/media/upload-init \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{

Static analysis

No suspicious patterns detected.