T09 · Insecure Skill Coding Practices
Error
- Location
SKILL.md:6- Finding
Shell Command Injection Through Unescaped PubMed Search Input
- Content
View full analysis
- Remediation
View remediation
Security audit
医学文献检索
Security checks for vulnerabilities and agentic risk
Overview
This PubMed literature-search skill is mostly coherent, but its documented curl command can become unsafe if a user query is inserted directly into a shell command.
Review before installing. The skill should be changed to use a structured HTTP request or curl with --get and --data-urlencode for the search term, and it should avoid placing user-provided queries directly inside shell command strings. The medical-literature purpose itself is reasonable, but do not use the shown command pattern with untrusted input as written.
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)
Vulnerability Patterns
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The trigger list includes several very broad phrases such as 'PubMed' and 'find papers', which can cause the skill to activate in contexts the user did not intend. In a medical-literature skill, unintended activation can misroute health-related queries, produce unsought medical research summaries, and interfere with safer or more appropriate routing to general medical-information workflows.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The evidence-quality section presents explanatory text in Chinese while the rest of the skill is in English, without indicating that language selection is optional or user-configurable. This can impose a language/locale assumption on users and does not document any justification for the mixed-language output.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The manifest names the skill as "医学文献检索" while the rest of the description is in English, indicating a locale-specific label without any stated user choice or justification. This can violate language/locale policy expectations when users are not given an opt-in or explanation for the enforced language.
- Content