Security audit

ANCC

Security checks for vulnerabilities and agentic risk

Overview

The skill appears purpose-aligned, but it recommends installing a mutable external CLI that can inspect credential and history locations without enough documented safeguards.

Install only if you trust the publisher and preferably pin a reviewed version with checksum or signature verification. Run audit commands deliberately as a normal user, avoid sudo and shared or secret-bearing CI contexts, and treat any audit output as sensitive before placing it in logs or agent context.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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 (3)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:49
Finding: Insufficiently Bounded Access to Credential and History Locations
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:31
Finding: Mutable and Unverified External Executable Installation
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Note

Location: SKILL.md:143
Finding: CI Workflow Uses a Mutable Third-Party Action Reference
Content: View full analysis
Remediation: View remediation
`. 2. Record the corresponding release tag in a comment for maintainability while retaining the immutable SHA. 3. Use dependency automation to propose and review controlled SHA updates. 4. Apply least-privilege workflow permissions, such as read-only repository contents unless write access is essential. 5. Do not expose secrets to the validation step unless strictly required. 6. Review upstream changes and release provenance before updating the pinned revision. ]]>

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (1)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The skill explicitly promotes ancc audit as an environment security check and states it scans sensitive local locations such as ~/.ssh, ~/.aws, history files, and skill configs, but it does not include an explicit warning about inspecting highly sensitive credential material or guidance on safe handling of results. In an agent context, users may invoke this automatically or on shared systems without realizing the scan scope, increasing the risk of unintended exposure of secrets in logs, outputs, or downstream tool processing.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.