Security audit

.Publish Temp

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for installing and using a news-fetching CLI, with the main caution being normal supply-chain risk from installing a third-party package from GitHub.

Install it in a dedicated virtual environment under a non-privileged account, review the upstream news-fetcher repository before use, and prefer an immutable commit or verified release if you need stronger supply-chain assurance.

A.I.G

Vulnerability Patterns

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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:32
Finding: Unverified Third-Party Package Installation from a Mutable Git Tag
Content: View full analysis
Remediation: View remediation
" ``` 2. Prefer a signed release artifact from a trusted package repository. Publish and document the expected SHA-256 hash, then require hash verification during installation. 3. Pin all transitive dependencies in a reviewed lockfile. Where supported, install with: ```bash pip install --require-hashes -r requirements.txt ``` 4. Verify release signatures or attestations and document how users can validate the artifact before execution. 5. Remove the unconditional `pip install --upgrade pip` instruction unless a specific minimum version is required. If required, pin and verify the installer version. 6. Continue using a dedicated virtual environment and recommend execution under a non-privileged account without unnecessary credentials in its environment. 7. Review the referenced commit and its dependency graph before updating the pinned version. Automated dependency and provenance checks should be incorporated into the release process. ]]>

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

Static analysis

No suspicious patterns detected.