ClawHub
Back to skill

Security audit

EpidBot

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed EpidBot API guide whose network access, uploads, authentication, and dataset publishing behavior fit its public-health analysis purpose.

Before installing, confirm you trust the EpidBot service and only send data you are authorized to share. Be especially careful with personally identifiable or regulated health data, and require explicit confirmation before publishing any dataset publicly.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

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 73)May include surrounding context.

md
| Publish dataset | `POST /api/v1/uploads/{dataset_id}/publish` | Makes a private dataset visible to **all** users — potential public disclosure of sensitive data. |

> **Delete endpoints are intentionally omitted.** This skill does not document
> `DELETE /api/v1/uploads/{dataset_id}`, `DELETE /api/v1/plots/{plot_id}`, or
> `POST /api/v1/plots/bulk-delete` to prevent automated data loss. Do not call
> them. Direct users to the EpidBot web UI at
> `https://kwar-ai.com.br/epidbot` to manage deletion manually.

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 73)May include surrounding context.

md
| Publish dataset | `POST /api/v1/uploads/{dataset_id}/publish` | Makes a private dataset visible to **all** users — potential public disclosure of sensitive data. |

> **Delete endpoints are intentionally omitted.** This skill does not document
> `DELETE /api/v1/uploads/{dataset_id}`, `DELETE /api/v1/plots/{plot_id}`, or
> `POST /api/v1/plots/bulk-delete` to prevent automated data loss. Do not call
> them. Direct users to the EpidBot web UI at
> `https://kwar-ai.com.br/epidbot` to manage deletion manually.

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 94)May include surrounding context.

Option 2: Username/Password (Returns JWT tokens)

bash
curl -X POST "$EPIDBOT_BASE_URL/api/v1/auth/login" \
  -H "Content-Type: application/json" \
  -d '{"username": "user", "password": "pass"}'

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 120)May include surrounding context.

md
## API Base URL

Default: `https://api.epidbot.kwar-ai.com.br/api/v1`

Configure via `EPIDBOT_BASE_URL` environment variable.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill repeatedly sets "locale": "en" in examples and message formats, which can steer agents to force English responses by default. Because the file does not pair this with guidance to honor the user's preferred language or make locale selection optional, it risks violating language/locale choice expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The canonical chat request example includes "locale": "en", which presents English as the default operating language. Without accompanying guidance to respect the user's language preference, this can lead downstream agents to impose a language choice without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The WebSocket start payload includes "locale": "en" as the only documented example, again biasing implementations toward English-only behavior. This is a natural-language policy concern because it does not document user choice or a justified locale restriction.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.