Security audit

pr-prep

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed pull-request preparation workflow that runs normal repository checks and drafts a PR description, with no evidence of hidden execution, exfiltration, or persistence.

Install only if you want an agent to run repository quality checks and draft PR text. Review the chosen output path before use, and be aware that formatter or fix steps may change local files as part of normal PR preparation.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (7)

Direct Prompt Extraction

High

Category: System Prompt Leakage
Confidence: 85% confidence
Finding: Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
Content: Scanner excerpt · SKILL.md (reported line 127)May include surrounding context.
md
If the description contains slop, apply `Skill(scribe:doc-generator)` principles to ground claims with specifics, remove marketing language, and use direct statements. ## Output Instructions Write the final PR description to the specified path, then display the file path and its contents for confirmation.

Anti-Refusal Statement

High

Category: Anti-Refusal
Confidence: 80% confidence
Finding: Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
Content: Scanner excerpt · modules/pr-template.md (reported line 52)May include surrounding context.
md
- `make lint` - no warnings

Anti-Refusal Statement

High

Category: Anti-Refusal
Confidence: 80% confidence
Finding: Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
Content: Scanner excerpt · modules/pr-template.md (reported line 245)May include surrounding context.
md
## Quality Gate Checklist - [ ] Formatting passes (no diffs after format command) - [ ] Linting passes (no warnings or errors) - [ ] All tests pass locally - [ ] Type checking passes (if applicable) - [ ] Build succeeds (if applicable)

Anti-Refusal Statement

High

Category: Anti-Refusal
Confidence: 80% confidence
Finding: Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
Content: Scanner excerpt · modules/quality-gates.md (reported line 99)May include surrounding context.
md
## Quality Gate Checklist - [ ] Formatting passes (no diffs after format command) - [ ] Linting passes (no warnings or errors) - [ ] All tests pass locally - [ ] Type checking passes (if applicable) - [ ] Build succeeds (if applicable)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The manifest lists generic triggers like "git", "pr", and "testing", plus a broad natural-language condition "completing a feature and ready for review." These overlap with common development conversation and do not define clear boundaries or exclusions, increasing the chance of unintended activation.
Content: No source excerpt is available for this finding.

Overly Broad Trigger

Low

Category: Trigger Abuse
Confidence: 70% confidence
Finding: Overly Broad Trigger: 'pr' is too short and may match unintended inputs
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill explicitly instructs writing a PR description to a file without warning the agent to confirm the destination path or obtain user approval before modifying files. In an agent setting, that can lead to unintended writes, overwriting user content, or creating artifacts in sensitive locations if the path is ambiguous or attacker-controlled.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.