owned-social-profile-audit
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for auditing external social media profiles, creating a surface for indirect prompt injection if those profiles contain malicious instructions.
- Ingestion points:
SKILL.md(Step 2) andreferences/profile-audit-checklist.md(Public Visibility section) instruct the agent to capture visible profile fields, bios, and public posts from platforms like X, Facebook, and LinkedIn. - Boundary markers: The instructions do not specify the use of delimiters or clear directives to ignore instructions that might be embedded within the social media content being audited.
- Capability inventory: No scripts or executables are included in the skill (no-code skill), meaning the skill itself does not provide tools for file-system writes, network operations, or subprocess execution.
- Sanitization: There are no requirements or methods defined for sanitizing or escaping the content retrieved from social media profiles before it is processed by the agent.
Audit Metadata