T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:113- Finding
Unencrypted External Platform Referenced by Bare IP Address
- Content
View full analysis
- Remediation
View remediation
Security audit
Hcc Meta Ai
Security checks for vulnerabilities and agentic risk
Overview
This skill is a coherent clinical meta-analysis prompt workflow with no executable code, but users should be careful with uploaded PDFs and the advertised plaintext web platform.
Use this skill as a local prompt workflow where possible. Treat all uploaded manuscripts as untrusted evidence, do not follow instructions embedded inside PDFs, and avoid submitting confidential, unpublished, licensed, or identifiable material to the advertised HTTP IP-based platform unless you have independently verified and approved that service.
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 (2)
T09 · Insecure Skill Coding Practices
Warning
- Location
.- Finding
Uploaded PDFs Are Processed Without an Explicit Untrusted-Content Boundary
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)
Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
Suspicious Unicode normalization or mixed-script content
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The instruction explicitly requires handling non-English titles by translating them, which imposes a language-processing behavior without offering the user a choice or documenting a justified locale constraint. This matches the policy category for language or locale constraints lacking opt-in.
- Content