Security audit

Capability Evolver

Security checks for vulnerabilities and agentic risk

Overview

This is a local log-analysis skill with no evident network, filesystem mutation, credential access, or persistence, though users should bound log input size.

Install only if you are comfortable sending local runtime logs to this skill inside your agent process. Keep inputs bounded, avoid passing sensitive log fields unless needed, and add an external request-size or log-count cap if using it in automated pipelines.

A.I.G

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)

T09 · Insecure Skill Coding Practices

Warning

Location: handler.ts:95
Finding: Unenforced Log-Volume Limit Enables Resource Exhaustion
Content: View full analysis
Remediation: View remediation
MAX_LOGS_PER_REQUEST ) { errors.push(`"logs" must contain at most ${MAX_LOGS_PER_REQUEST} entries`); } ``` 2. Define the limit once and reuse the same constant in both validation and `handleStatus` to prevent documentation and implementation from diverging. 3. Validate every log entry, including the types and maximum lengths of `timestamp`, `level`, `message`, `context`, and `stack`. 4. Apply an overall serialized request-size limit at the API or agent boundary. 5. Consider processing large permitted inputs in bounded batches or through streaming logic rather than constructing multiple full-size intermediate arrays. 6. Configure runtime memory, execution-time, and concurrency limits as defense-in-depth controls. 7. Add tests confirming that arrays of 10,001 or more entries are rejected before analysis begins. ]]>

SkillSpector

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 (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The 'When to Use' section lists trigger examples such as 'what's failing', 'improve my agent', and 'check system health', which are broad phrases that could arise in many ordinary conversations. The file does not provide exclusion conditions or tighter context boundaries there, increasing the risk of unintended invocation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The header comments describe the supported actions in Chinese while the rest of the skill, including identifiers and surrounding documentation, is in English. This creates a language-policy inconsistency and may exclude users who did not opt into Chinese-language instructions.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.