viral-post-writer
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, suspicious dependencies, or privilege escalation attempts were detected. The skill logic is confined to content generation and web research as described in its purpose.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes untrusted data from web searches and user inputs without using explicit boundary markers before interpolating that data into generation templates. This is considered a low risk inherent to the use case.
- Ingestion points: Product details and personal experience provided via the input schema in SKILL.md, and external research data retrieved through web_search and web_browse tools.
- Boundary markers: The workflow does not define specific delimiters or instructions to ignore embedded commands within the ingested product data or search results.
- Capability inventory: The skill is capable of performing web searches, browsing web pages, and generating text output for multiple social media platforms.
- Sanitization: No specific sanitization, escaping, or validation of external content is present in the skill instructions.
Audit Metadata