strategy-personal-brand
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection as it processes untrusted user data to generate strategies.
- Ingestion points: The 'Required Input' section identifies multiple fields for user-provided data, including 'Individual's name', 'professional role', and 'Current online presence'.
- Boundary markers: The skill lacks explicit delimiters (e.g., XML tags or triple quotes) to isolate user-supplied inputs within the processing logic.
- Capability inventory: The skill possesses no dangerous capabilities; it does not utilize file writing, network requests, or subprocess execution.
- Sanitization: There are no instructions for sanitizing or escaping the content provided by the user before interpolation into the output markdown.
- [SAFE]: The skill uses established marketing frameworks (e.g., KNOWN, VCP, POEM) and references reputable platforms (LinkedIn, Facebook, X, TikTok) and tools (Buffer, Hootsuite) in a manner consistent with its stated purpose of personal branding strategy.
Audit Metadata