Security audit

Recursive Generosity Protocol (Delta9-WP-003)

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only ethical guidance skill with no executable behavior, though one Markdown table has malformed carriage-return formatting that should be cleaned up.

Installers should treat this as a non-executable guidance skill. Because it discusses workplace metrics and policy proposals, use it only for transparent, stakeholder-reviewed planning, and ask the publisher to normalize the malformed Markdown line before relying on the reference table.

A.I.G

Vulnerability Patterns

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

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Ae4

Medium

Category: analysis-evasion
Confidence: 93% confidence
Finding: The file contains suspicious Unicode/control-character artifacts, including a malformed path entry in the canonical references table that appears to include hidden or non-printable characters. Such characters can be used to visually disguise content, break parser behavior, or cause reviewers and tools to miss referenced files, which is especially risky in security-relevant documentation that says references/SECURITY.md must be read first.
Content: No source excerpt is available for this finding.

Ae4

Medium

Category: analysis-evasion
Confidence: 80% confidence
Finding: Suspicious Unicode normalization or mixed-script content
Content: No source excerpt is available for this finding.

Ae4

Medium

Category: analysis-evasion
Confidence: 80% confidence
Finding: Suspicious Unicode normalization or mixed-script content
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.