Back to skill

Security audit

Proposal & SOW Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward writing aid for freelancer proposals and does not request system access, credentials, persistence, or code execution.

Before sending generated proposals to clients, review pricing, terms, currency, locale, and legal language for your own business and region. Installing this skill does not appear to grant it sensitive system access.

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
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

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

This markdown file includes example invocations for the skill, but it does not specify whether only /proposal-generator ... commands should trigger it or whether broader natural-language requests about proposals might also activate the skill. Without explicit trigger constraints or negative examples, there is some ambiguity about activation boundaries.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The tone rules state 'UK English by default' and only switch to US if specified. This imposes a locale/language preference unless the user proactively requests otherwise, which is a natural-language policy concern under the language/locale rule.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.