Security audit

Press Media Relations

Security checks for vulnerabilities and agentic risk

Overview

The skill’s media-relations workflow is coherent, but its manifest advertises read-only capability while the instructions ask to persist launch plans, claims, and embargo commitments.

Review before installing. The skill appears to be a legitimate launch PR workflow, but it should be installed only in an environment that either updates its declared capabilities to include the described writes or strictly enforces the current read-only manifest and treats all proposed registry/memory changes as explicit user approvals.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: distribution-manifest.json:2
Finding: Declared read-only capabilities conflict with persistent write instructions
Content: View full analysis
.md` — see [Skill Contract](../../../references/skill-contract.md) §Save Results Template. First ask: "Save these results for future sessions?" Registry-class facts (embargo com ...[truncated 3329 chars]
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

Static analysis

No suspicious patterns detected.