creator-profile-teardown
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted content from external social media profiles.
- Ingestion points: Metadata, posts, and transcripts/comments are fetched via
WebFetchduring the profiling workflow (SKILL.md). - Boundary markers: The prompt instructions lack explicit delimiters or specific warnings to ignore instructions found within the fetched data.
- Capability inventory: The skill is configured to use
Bash,Read,Write, andWebFetchtools. - Sanitization: There are no specific instructions for validating or sanitizing external content before it is processed by the agent.
Audit Metadata