T07 · Tool Hijacking and Spoofing
- Location
scripts/__init__.py:10- Finding
Unvalidated Python Module Search Path Enables Local Module Hijacking
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This is a coherent memory-management skill, but it stores and indexes user-provided content with unclear retention/control and imports an external local M-Flow package through an unsafe path mechanism.
Review this skill before installing if you may handle private or sensitive conversations. Use it only when you intentionally want content persisted into M-Flow memory, confirm where M-Flow stores data, how to delete it, and who or what agents can search it. Also ensure the sibling m_flow dependency path is trusted and not writable by untrusted users.
scripts/__init__.py:10Unvalidated Python Module Search Path Enables Local Module Hijacking
SKILL.md:57Dependency Installation Instructions Do Not Enforce Package Integrity
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
HF_HUB_OFFLINE=1
### .env 配置 (m_flow/.env)
LLM_PROVIDER="ollama" LLM_MODEL="ollama/qwen2.5:14b-instruct-q8_0"
Most of the operational instructions, activation conditions, and usage guidance are presented only in Chinese, which effectively forces a specific language on users. The file does not indicate that this is a region-specific skill or offer an alternative language option.
The activation criteria are broad enough that the skill could trigger on ordinary user requests involving search, knowledge, or memory, causing persistence or retrieval actions without clear user intent. In a memory-management skill, ambiguous activation increases the chance of over-collection and unintended processing of conversation content.
The skill demonstrates adding, indexing, and searching memory content but does not warn that user conversations or knowledge points may be stored and processed persistently. This creates a privacy and consent risk because users may disclose sensitive information without realizing it will enter a long-lived memory system.
The file’s natural-language strings and comments indicate the skill is explicitly framed as a Chinese-language test script, with no indication that language selection is optional. Under the policy, forcing a specific language without user opt-in is a locale/language policy violation.
The documentation includes endpoint and API-key style environment variables in a .env configuration example without guidance on protecting credentials or avoiding accidental disclosure. Even though the sample uses local Ollama and a placeholder key, normalizing plaintext secret handling can lead operators to place real credentials in insecure files or commit them to source control.