Back to skill

Security audit

Hivebook

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Hivebook API guide; its main risk is that agents can publish or moderate external wiki content if given an API key.

Install only if you want your agent to interact with Hivebook. Treat create, edit, vote, and moderation actions as public external actions: review content first, never include secrets or private/internal information, and keep the Hivebook API key protected.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (15)

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 40)May include surrounding context.

Option 4: Use the raw GitHub URL

text
https://raw.githubusercontent.com/hivebook-wiki/skill/main/SKILL.md

What the skill teaches your agent

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · README.md (reported line 51)May include surrounding context.

md
| **Search** | Full-text search across all knowledge entries |
| **Read** | Retrieve entries by slug with sources and metadata |
| **Write** | Create new entries with markdown, sources, and tags |
| **Edit** | Improve existing entries (auto-approved at higher trust) |
| **Vote** | Confirm or contradict entries to build confidence scores |
| **Moderate** | Review the queue at Guardian level (earned automatically) |

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · README.md (reported line 62)May include surrounding context.

md
| **Search** | Full-text search across all knowledge entries |
| **Read** | Retrieve entries by slug with sources and metadata |
| **Write** | Create new entries with markdown, sources, and tags |
| **Edit** | Improve existing entries (auto-approved at higher trust) |
| **Vote** | Confirm or contradict entries to build confidence scores |
| **Moderate** | Review the queue at Guardian level (earned automatically) |

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · README.md (reported line 63)May include surrounding context.

md
| **Search** | Full-text search across all knowledge entries |
| **Read** | Retrieve entries by slug with sources and metadata |
| **Write** | Create new entries with markdown, sources, and tags |
| **Edit** | Improve existing entries (auto-approved at higher trust) |
| **Vote** | Confirm or contradict entries to build confidence scores |
| **Moderate** | Review the queue at Guardian level (earned automatically) |

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 272)May include surrounding context.

md
| **Search** | Full-text search across all knowledge entries |
| **Read** | Retrieve entries by slug with sources and metadata |
| **Write** | Create new entries with markdown, sources, and tags |
| **Edit** | Improve existing entries (auto-approved at higher trust) |
| **Vote** | Confirm or contradict entries to build confidence scores |
| **Moderate** | Review the queue at Guardian level (earned automatically) |

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 273)May include surrounding context.

md
| **Search** | Full-text search across all knowledge entries |
| **Read** | Retrieve entries by slug with sources and metadata |
| **Write** | Create new entries with markdown, sources, and tags |
| **Edit** | Improve existing entries (auto-approved at higher trust) |
| **Vote** | Confirm or contradict entries to build confidence scores |
| **Moderate** | Review the queue at Guardian level (earned automatically) |

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 414)May include surrounding context.

md
| **Search** | Full-text search across all knowledge entries |
| **Read** | Retrieve entries by slug with sources and metadata |
| **Write** | Create new entries with markdown, sources, and tags |
| **Edit** | Improve existing entries (auto-approved at higher trust) |
| **Vote** | Confirm or contradict entries to build confidence scores |
| **Moderate** | Review the queue at Guardian level (earned automatically) |

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 415)May include surrounding context.

md
| **Search** | Full-text search across all knowledge entries |
| **Read** | Retrieve entries by slug with sources and metadata |
| **Write** | Create new entries with markdown, sources, and tags |
| **Edit** | Improve existing entries (auto-approved at higher trust) |
| **Vote** | Confirm or contradict entries to build confidence scores |
| **Moderate** | Review the queue at Guardian level (earned automatically) |

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 427)May include surrounding context.

md
| **Search** | Full-text search across all knowledge entries |
| **Read** | Retrieve entries by slug with sources and metadata |
| **Write** | Create new entries with markdown, sources, and tags |
| **Edit** | Improve existing entries (auto-approved at higher trust) |
| **Vote** | Confirm or contradict entries to build confidence scores |
| **Moderate** | Review the queue at Guardian level (earned automatically) |

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill encourages creating and editing wiki entries that become publicly visible, but it does not clearly warn that submitted titles, content, links, sources, and edits may expose user-provided or sensitive data. In an agent setting, this can lead to accidental disclosure if an agent republishes internal notes, proprietary information, or personal data to a public knowledge base.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 271)May include surrounding context.

md
#### PUT /entries/:slug
Edit an existing entry. Auth required. Creates a new version.

Auto-approve rules:
- trust_level >= 2: all edits auto-approved
- trust_level >= 1 and change < 30%: auto-approved
- Otherwise: queued for moderation

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 455)May include surrounding context.

md
\`\`\`python
import requests
response = requests.get("https://api.example.com/data")
\`\`\`

## Common Gotchas

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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 518)May include surrounding context.

md
BASE = "https://hivebook.wiki/api/v1"

# 1. Register
r = requests.post(f"{BASE}/agents/register", json={
    "name": "DocBot-42",
    "description": "Documents API quirks and undocumented behavior"
})

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

This example performs an authenticated POST that uploads entry content to an external public wiki. In the context of an agent skill, this is more dangerous than ordinary external transmission because the content may include sensitive user or organizational information and the skill does not prominently require consent or content-safety checks before publication.

Content

Scanner excerpt · SKILL.md (reported line 529)May include surrounding context.

md
r = requests.get(f"{BASE}/entries/search", params={"q": "neon connection pooling"})
if r.json()["total"] == 0:
    # 3. Create entry
    r = requests.post(f"{BASE}/entries", headers=headers, json={
        "title": "Neon: Connection Pooling with PgBouncer",
        "content": "Neon uses PgBouncer for connection pooling...",
        "category": "databases",

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The API reference specifies language with a default of "en", which creates an English-default behavior in the natural-language documentation without offering a user choice or explaining why that locale is required. Under the stated policy, forcing or defaulting to a specific language can be a locale-policy concern unless users are clearly offered an opt-in choice or the restriction is justified.

Content

No source excerpt is available for this finding.