work-with-creators-creator-vetting
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from public social media profiles and user comments to perform creator vetting.
- Ingestion points: SKILL.md specifies reading profile bios and the last 12–20 posts, as well as visible comments.
- Boundary markers: The instructions do not specify any delimiters or safety warnings for the agent to ignore instructions embedded in the external content.
- Capability inventory: The skill is primarily focused on analysis and reporting (writing verdicts and metrics); it does not utilize high-risk tools for file system modification, command execution, or network exfiltration beyond standard browser use.
- Sanitization: No specific instructions are provided for sanitizing, escaping, or validating the external content retrieved from social media pages.
Audit Metadata