argue-the-opposite
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to take a user-supplied position and generate counter-arguments.
- Ingestion points: User-provided position text.
- Boundary markers: None.
- Capability inventory: None beyond standard text generation; the skill does not use tools, perform file operations, or make network requests.
- Sanitization: None.
- [EXTERNAL_DOWNLOADS]: The documentation provides links to the author's GitHub repository for installation and source code access.
- [SAFE]: The skill's instructions are limited to internal reasoning and perspective-taking. No malicious code, obfuscation, or unauthorized access attempts were identified.
Audit Metadata