Remove AI slop

• Outcome: Pass
• Latest audit: Oct 4, 2026 · 5:00 AM UTC
• Version: 1.0.0

Overview

This is a markdown-only editing skill that rewrites prose for clarity and does not request code execution, persistence, credentials, or broad system access.

Install this when you want an agent to rewrite drafts more directly. Review the output before publishing because the skill intentionally changes wording and punctuation, and the plain-punctuation default may not fit every brand, dialect, or literary style unless you specify your preference.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Rogue Agent: Self-Modification, Session Persistence
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Session Persistence

Medium

• Category: Rogue Agent
• Confidence: 75% confidence

Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · references/patterns.md (reported line 26)May include surrounding context.

md

| Excessive punctuation | Are dashes, semicolons, parentheses, or ellipses repeatedly carrying avoidable asides? Simplify the sentence. | Meaningful punctuation, exact quotations, and the author's style. |
| Meaning drift | Did smoothing remove “not,” “may,” an exception, a date, an attribution, or a criticism? Restore the distinction. | Every material qualification, even if the sentence becomes longer. |

Do not strip uncertainty indiscriminately. “May,” “approximately,” and “in this sample” can carry the most important information in a sentence. Do not turn accessibility guidance into a demand for uniformly short sentences or simplistic vocabulary.

When reviewing multiple supplied drafts, check recurring openings and constructions across them. With only one draft, assess what is present rather than claiming a repetition rate. Never introduce random synonyms, line breaks, or errors to satisfy a superficial “human” score.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 77% confidence

Finding

Line L023 instructs the editor to 'default to the plain-punctuation style' with specific formatting constraints such as straight quotes and no emoji. This is a natural-language style/locale preference imposed by default rather than presented as an opt-in choice, though it is partially mitigated by noting that the user's explicit house style or literary voice takes priority.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 74% confidence

Finding

Line L088 again directs the editor to apply a 'plain-punctuation default' to business prose by removing dash asides, smart quotes, and decorative emoji. Because this is presented as a default behavioral rule rather than a user-selected option, it can conflict with organizational policy against forcing a specific language/locale or style choice without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.