T09 · Insecure Skill Coding Practices
Error
- Location
top_asv_blast.py:65- Finding
Unsanitized sample names allow file overwrite outside the output directory
- Content
View full analysis
- Remediation
View remediation
Security audit
species_identification_sequence_blast_annotation_tool
Security checks for vulnerabilities and agentic risk
Overview
The skill is a coherent BLAST annotation helper, but one script can write CSV output outside the chosen results directory when sample names come from an untrusted OTU table.
Install and run this only in an isolated project directory or virtual environment, avoid using administrator privileges, and do not process proprietary or sensitive sequence data unless you are comfortable sending it to NCBI. Treat OTU tables as trusted input until sample-name sanitization is added, because crafted headers can cause result files to be written outside the intended output folder.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
Findings (2)
T08 · Insecure Dependencies
Note
- Location
SKILL.md:15- Finding
Biopython dependency is installed without version or integrity pinning
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
该触发短语过于通用，容易与普通用户关于BLAST注释的自然提问重叠，导致技能在缺乏明确调用意图时被误触发。误触发本身不一定直接造成系统被攻破，但可能让代理在错误上下文中调用外部生物信息流程、产生不必要的网络请求或处理非预期数据。
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The script sends raw biological sequences to NCBI over the network via NCBIWWW.qblast without any explicit user warning, consent step, or privacy notice. If the input sequences are unpublished, proprietary, regulated, or tied to sensitive sample metadata, this can cause unintended external disclosure to a third party.
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 80% confidence
- Finding
“BLAST物种注释指南”更像一般性文档标题或帮助请求，而不是边界清晰的调用命令，因此可能在普通问答场景中被意外匹配。相比前一个短语，其危险性较低，因为它更偏说明性，但仍会增加技能选择歧义并导致非预期激活。
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
SQP-3 applies to all file types and covers language/locale policy violations. This script’s module docstring is Chinese-only, and the same language constraint continues in user-facing print statements, with no opt-in, alternative language, or stated region-specific requirement.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The file's docstring, CLI description, help text, and runtime messages are all written in Chinese, which imposes a specific language on users. There is no indication that language selection is optional or that the tool is explicitly limited to a Chinese-speaking context.
- Content
Static analysis
No suspicious patterns detected.