Security audit

Ask-More

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its multi-model consultation purpose, but it needs review because it includes an exploitable config-validation helper and under-disclosed external-model data flow.

Review before installing. Use only if you are comfortable sending the packed question, and possibly recent conversation context in full mode, to the configured model providers. Reset privacy_acknowledged to false if you want the first-use privacy notice shown, and avoid running scripts/load-config.sh on untrusted or unusual skill paths until the path interpolation bug is fixed.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Error

Location: scripts/load-config.sh:23
Finding: Python Code Injection Through an Attacker-Controlled Skill Directory Path
Content: View full analysis
" ``` 4. The script inserts the malicious path into the `python3 -c` source string. 5. The injected characters terminate the intended `open('...')` argument and introduce attacker-selected Python statements. 6. Python executes those statements during what appears to be routine configuration validation. Successful exploitation requires control over, or influence on, th ...[truncated 758 chars]
Remediation: View remediation

T01 · Skill Instruction Hijacking

Warning

Location: references/prompt-templates.md:39
Finding: Prompt Injection Through Untrusted Model Responses in the Synthesis Prompt
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (3)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The privacy notice is written only in Chinese and is presented as the required first-use disclosure, with no indication that the user can choose another language. This is a natural-language locale policy issue because the skill imposes a specific language on users rather than offering a language/locale choice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The editable confirmation template is entirely in Chinese, and later report templates are also specified in Chinese-only wording. Because these are prescribed user-facing outputs and no opt-in or locale selection is offered, the skill violates the language/locale policy criteria.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The instruction "Write in the same language as the original question" imposes a language-selection policy in natural language. Under the stated policy, forced language/locale behavior is a violation unless the skill offers user choice or documents a justified regional constraint, which this file does not do.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.