marketing-influencer
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches and installs the
agent-browsertool from Vercel Labs' official GitHub repository, which is a well-known and trusted source.- [COMMAND_EXECUTION]: It utilizes theagent-browserCLI to perform research tasks on social media platforms and generate local campaign assets.- [PROMPT_INJECTION]: The skill demonstrates a vulnerability surface for indirect prompt injection through its web scraping functionality. - Ingestion points: The skill uses
agent-browser get text bodyto ingest content from TikTok, Instagram, and YouTube profiles during the research phase. - Boundary markers: Absent; there are no explicit instructions to use delimiters or ignore instructions within the scraped text.
- Capability inventory: The skill can execute shell commands (
agent-browser) and perform local file writes for reports and screenshots. - Sanitization: Absent; the skill does not explicitly sanitize the external content retrieved from social media platforms before processing.
Audit Metadata