Back to skill

Security audit

Fox Ontology

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local ontology memory tool, but its code does not enforce the validation and secret-handling protections its documentation promises.

Review this before installing if you expect strong validation or safe credential handling. Do not store passwords, tokens, API keys, or other secrets in this ontology graph; use only secret references, and validate or audit the graph after mutations until the skill enforces schema checks before writing.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/ontology.py:121
Finding

Graph Mutations Bypass Schema Validation and Permit Plaintext Sensitive Data

Content
View full analysis
dict: """Create a new entity.""" entity_id = entity_id or generate_id(type_name) timestamp = datetime.now(timezone.utc).isoformat() entity = { "id": entity_id, "type": type_name, "properties": properties, "created": timestamp, "updated": timestamp } record = {"op": "create", "entity": entity, "timestamp": timestamp} append_op(graph_path, record) return entity ``` Update and relation operations follow the same write-before-validation pattern: ```python def update_entity(entity_id: str, properties: dict, graph_path: str) -> dict | None: """Update entity properties.""" entities, _ = load_graph(graph_path) if entity_id not in entities: return None timestamp = datetime.now(timezone.utc).isoformat() record = {"op": "update", "id": entity_id, "properties": properties, "timestamp": timestamp} append_op(graph_path, record) entities[entity_id]["properties"].update(properties) entities[entity_id]["updated"] = timestamp return entities[entity_id] ``` ```python def create_relation(from_id: str, rel_type: str, to_id: str, properties: dict, graph_path: str): """Create a relation between entities.""" timestamp = datetime.now(timezone.utc).isoformat() record = { "op": "relate", "from": from_id, "rel": rel_type, "to": to_id, "properties": properties, "times ...[truncated 4106 chars]
Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (13)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 84)May include surrounding context.

md
python3 scripts/ontology.py create --type Person --props '{"name":"Alice","email":"alice@example.com"}'

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 90)May include surrounding context.

md
python3 scripts/ontology.py create --type Person --props '{"name":"Alice","email":"alice@example.com"}'

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 91)May include surrounding context.

md
python3 scripts/ontology.py create --type Person --props '{"name":"Alice","email":"alice@example.com"}'

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 92)May include surrounding context.

md
python3 scripts/ontology.py create --type Person --props '{"name":"Alice","email":"alice@example.com"}'

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 98)May include surrounding context.

md
python3 scripts/ontology.py create --type Person --props '{"name":"Alice","email":"alice@example.com"}'

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 104)May include surrounding context.

md
python3 scripts/ontology.py create --type Person --props '{"name":"Alice","email":"alice@example.com"}'

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 212)May include surrounding context.

md
python3 scripts/ontology.py create --type Person --props '{"name":"Alice","email":"alice@example.com"}'

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 221)May include surrounding context.

md
python3 scripts/ontology.py create --type Person --props '{"name":"Alice","email":"alice@example.com"}'

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 222)May include surrounding context.

md
python3 scripts/ontology.py create --type Person --props '{"name":"Alice","email":"alice@example.com"}'

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 · references/schema.md (reported line 165)May include surrounding context.

forbidden_properties: [password, secret, token, key, api_key] properties: service: string secret_ref: string # Reference to secret store (e.g., "keychain:github-token") expires: datetime? scope: string[]?

text

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding

The skill explicitly documents write access to workspace files and directory creation, but it does not declare any tool scope or allowed-tools boundary. That makes the skill's effective capabilities broader and less auditable, increasing the risk that an agent activates it and performs unintended file mutations to shared memory or adjacent workspace content.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough to match common conversational requests such as 'remember' or 'what do I know about', which can cause the skill to activate in situations the user did not intend. In this skill, unintended activation is more dangerous because it can read and write shared persistent memory, creating privacy, integrity, and cross-skill state-manipulation risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The code implements entity deletion by appending a delete operation to the graph log, but this destructive action has no confirmation prompt and no warning comment or docstring indicating user-impact beyond the terse function name. For a code file, destructive operations should include some visible disclosure unless the warning is otherwise documented; nothing in this file indicates such a warning for deletion.

Content

No source excerpt is available for this finding.