SkillSpector · art

Without declared permissions the skill's intent is opaque and cannot be validated.

SKILL.md

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Lib/discord-bot.ts

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Lib/midjourney-client.ts

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Tools/GenerateMidjourneyImage.ts

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Tools/Generate.ts

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Tools/Generate.ts

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Workflows/RemoveBackground.md

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.

Workflows/Essay.md

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

Workflows/Mermaid.md

Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

Workflows/Mermaid.md

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Tools/Generate.ts

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Tools/Generate.ts

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Tools/Generate.ts

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Tools/GenerateMidjourneyImage.ts

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Tools/GenerateMidjourneyImage.ts

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Tools/GenerateMidjourneyImage.ts

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.

Workflows/RemoveBackground.md

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Tools/package.json

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Tools/package.json

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Tools/package.json