viral-reverse-engineering
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions are focused on analytical tasks and do not involve high-risk operations. No evidence of credential theft, data exfiltration, or malicious commands was found.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content such as video transcripts and social media comments, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: Transcripts, captions, and top comments enter the context via the processes described in references/sourcing-the-content.md.
- Boundary markers: None specified; instructions do not define specific delimiters or warnings to ignore instructions within the processed data.
- Capability inventory: Across all files, the skill's capabilities are limited to calling other content-focused skills such as hook-writer and tiktok-script.
- Sanitization: No input sanitization or escaping of untrusted external content is performed.
Audit Metadata