acf-local-json
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (HTML, designs) which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill analyzes user-provided HTML, designs, and images as described in
SKILL.md. - Boundary markers: There are no explicit instructions or delimiters to separate user-provided data from the agent's instructions.
- Capability inventory: The skill utilizes a local Python script
scripts/generate_keys.pyand has the capability to generate JSON files. - Sanitization: No specific sanitization or filtering logic is mentioned for the input HTML.
Audit Metadata