smm
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources including website URLs, social media comments, and community discussions, creating a potential surface for indirect prompt injection.
- Ingestion points: Website analysis via Playwright in 'references/carousel.md', social media comments and DMs in 'references/community.md', and thread scraping in 'references/social-intel.md'.
- Boundary markers: The skill contains explicit defensive instructions in 'references/creator-vetting.md', 'references/community.md', and 'references/content.md' that direct the agent to treat external content as data only and ignore any embedded directives.
- Capability inventory: The skill can execute shell commands via 'bash' and 'run_command' and perform file operations.
- Sanitization: Relies on explicit instructions to the model to maintain strict boundaries between data and instructions.
- [EXTERNAL_DOWNLOADS]: The skill utilizes several external tools and service integrations to fulfill its social media management objectives.
- Tools: Depends on the 'postiz' CLI for scheduling and 'yt-dlp' for harvesting video transcripts.
- APIs: Connects to Google's Gemini API for image generation and the Upload-Post.com API for publishing.
- Note: These tools and APIs are functional requirements for the skill's intended purpose and originate from well-known service providers.
Audit Metadata