social-ad
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill instructions are restricted to creative text generation and policy compliance checks.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing external landing page content to extract marketing details. This is assessed as safe as the skill use-case is limited to drafting copy and does not involve exploitable capabilities like shell access or file writing.
- Ingestion points: External landing page URLs referenced in Workflow step 1 of SKILL.md.
- Boundary markers: Absent; no specific delimiters are used to isolate untrusted content from instructions.
- Capability inventory: Restricted to text analysis and variant drafting; no dangerous tools or system permissions are requested.
- Sanitization: Absent.
Audit Metadata