Talking Head And Piece To Camera

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 10:19 AM UTC
• Version: 1.0.0

Overview

This skill is a coaching guide for filming talking-head videos and does not include executable code, hidden persistence, credential use, or unsafe automatic actions.

Install this if you want an agent to coach filming yourself on camera. Be aware it may route some general video-delivery questions to this skill, and publishing should still remain under your explicit control through the separate scheduling or WoopSocial workflow.

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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Anti-Refusal Statement

High

• Category: Anti-Refusal
• Confidence: 85% 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 · references/batch-filming-and-recipes.md (reported line 57)May include surrounding context.

md

desk shot → face), used on the profile and in social-proof-and-testimonials content. Trust layer human,
volume layer avatar, nobody shamed.

## Never
Judge a take you can't see, or fabricate "that looked natural" · prescribe a camera upgrade as the fix · shame a
camera-shy human onto camera · let a word-for-word prompter read ship when a beat-map riff was available · film
anyone else without consent · claim WoopSocial films, edits, or analyzes footage (publishing only) · sand a

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The skill description uses broad, common phrases like 'film myself' and 'I look stiff on camera' as invocation cues, which can cause the router to select this skill for ordinary conversational requests that only loosely relate to on-camera coaching. This is not a code-execution issue, but it can lead to unintended activation, incorrect routing, and downstream handling by the wrong skill, especially in multi-skill agent environments.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium

• Category: Excessive Agency
• Confidence: 75% confidence

Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/batch-filming-and-recipes.md (reported line 60)May include surrounding context.

md

## Never
Judge a take you can't see, or fabricate "that looked natural" · prescribe a camera upgrade as the fix · shame a
camera-shy human onto camera · let a word-for-word prompter read ship when a beat-map riff was available · film
anyone else without consent · claim WoopSocial films, edits, or analyzes footage (publishing only) · sand a
take past the point where the human sounds like themselves.

Vague Triggers

Low

• Category: Not specified by scanner
• Confidence: 79% confidence

Finding

This JSON manifest-like file contains a general description of the skill's purpose and behavior, but it does not specify concrete activation phrases, scope boundaries, or negative examples for when the skill should or should not be invoked. Because the description is broad coaching language about on-camera delivery, it could overlap with a wide range of generic video-help requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.